© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10750
    Prev
    Next
    INDEX
    Explanations

    phrases directly related to doing research or finding information

    oai_token-act-pair · gemini-2.0-flash

    investigation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Point
    -0.48
    olymers
    -0.47
     Besch
    -0.47
     دیکھیے
    -0.46
    惺
    -0.46
    TypeDef
    -0.45
     Not
    -0.45
     befre
    -0.44
    rec
    -0.44
    sig
    -0.44
    POSITIVE LOGITS
    iastes
    0.69
     itſelf
    0.68
     myſelf
    0.66
     Diſ
    0.66
     pleaſure
    0.65
     doInBackground
    0.65
     consultato
    0.64
     Reſ
    0.63
     ſhe
    0.63
     JpaRepository
    0.63
    Activations Density 0.710%

    No Known Activations