© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10181
    Prev
    Next
    INDEX
    Explanations

    a double underscore followed by other characters, often 'u' and a number, perhaps within a code or data structure context.

    oai_token-act-pair · gemini-2.0-flash

    symbols or characters used in coding or formatting

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

    \_\_

    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
     the
    -0.57
     بيها
    -0.56
    ochrome
    -0.54
    trägen
    -0.54
     Ar
    -0.53
    parole
    -0.52
    acas
    -0.52
    érard
    -0.52
    atra
    -0.51
    menter
    -0.51
    POSITIVE LOGITS
     beginnetje
    0.69
    principalColumn
    0.68
     XNUMX
    0.65
    Portail
    0.63
     onBind
    0.61
     oprot
    0.60
     HasFactory
    0.59
     Avez
    0.59
     Administrativna
    0.58
    esModule
    0.55
    Activations Density 2.352%

    No Known Activations