© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12709
    Prev
    Next
    INDEX
    Explanations

    words related to coding or nutrition deficits

    oai_token-act-pair · gemini-2.0-flash

    diferentes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    GenerationType
    -0.71
    slidesPer
    -0.69
    LLocation
    -0.68
     EdgeInsets
    -0.68
    SharedDtor
    -0.66
     برانيه
    -0.65
     BrowserModule
    -0.64
    脚注の使い方
    -0.64
     HasFactory
    -0.64
     GenerationType
    -0.64
    POSITIVE LOGITS
    batore
    0.50
    تقاوى
    0.47
     posé
    0.42
    まさ
    0.42
    ener
    0.42
    tender
    0.42
     pez
    0.40
     Alembic
    0.40
    PEZ
    0.40
     allemande
    0.40
    Activations Density 1.005%

    No Known Activations