© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 14065
    Prev
    Next
    INDEX
    Explanations

    articles, determiners and related words, sometimes near words like human or DNA

    oai_token-act-pair · gemini-2.0-flash

    words related to suggestions or recommendations

    np_token-act-pair-logits · gpt-4o-mini

    time

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reviews
    -0.65
     searches
    -0.65
     calls
    -0.63
     reports
    -0.63
     deals
    -0.61
     approaches
    -0.59
     tours
    -0.59
     requests
    -0.57
     answers
    -0.57
     responses
    -0.57
    POSITIVE LOGITS
     فريبيس
    0.95
     TextAppearance
    0.79
    AndEndTag
    0.71
    MigrationBuilder
    0.71
    Amicalement
    0.71
     suggestion
    0.68
     anecdote
    0.68
     allegation
    0.68
     recommendation
    0.67
    utives
    0.66
    Activations Density 5.084%

    No Known Activations