© 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. 9581
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to biological or chemical analyses and studies

    oai_token-act-pair · gemini-2.0-flash

    support and analysis terms

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

    supports

    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
     tartalomajánló
    -0.82
     Theſe
    -0.75
     كومونز
    -0.75
    jooq
    -0.71
     Efq
    -0.68
    ſelves
    -0.67
     مرئيه
    -0.66
     doubtnut
    -0.65
     comuniques
    -0.64
    ſelf
    -0.61
    POSITIVE LOGITS
     supports
    0.90
     support
    0.88
     supported
    0.76
     Support
    0.68
    Supports
    0.68
     Supports
    0.67
     onderste
    0.65
     provided
    0.65
    Support
    0.63
     indicates
    0.63
    Activations Density 4.889%

    No Known Activations