© 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. 9403
    Prev
    Next
    INDEX
    Explanations

    contextual prepositions: words that connect the situation to something.

    oai_token-act-pair · gemini-2.0-flash

    words indicating a process or progression

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

    Through

    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
     conseguenza
    -0.61
     sœurs
    -0.60
     facie
    -0.59
     poichè
    -0.59
     dovuto
    -0.56
     moitié
    -0.55
     namorados
    -0.55
     linkovi
    -0.54
    mektedir
    -0.54
    antMatchers
    -0.53
    POSITIVE LOGITS
     the
    0.66
    rokken
    0.60
     transfieras
    0.59
    randall
    0.57
     صوتيه
    0.57
    DockStyle
    0.55
     discussion
    0.54
     Monfieur
    0.54
     purpoſe
    0.54
     loops
    0.53
    Activations Density 7.816%

    No Known Activations