© 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. 11176
    Prev
    Next
    INDEX
    Explanations

    Australian organizations and places

    oai_token-act-pair · gemini-2.0-flash

    Australian

    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
    EVP
    -0.47
     Vieux
    -0.46
    OWSKI
    -0.45
    andoah
    -0.45
    monton
    -0.45
    box
    -0.43
    Aiheesta
    -0.42
    OPSIS
    -0.40
    Rnd
    -0.40
     rada
    -0.40
    POSITIVE LOGITS
    sizeCache
    0.83
    BufferException
    0.73
    PerformLayout
    0.73
    Билгалдахарш
    0.71
    principalColumn
    0.71
    LError
    0.67
     RIPRODUZIONE
    0.66
     لينك
    0.66
    encodeWith
    0.65
    ":[{
    0.63
    Activations Density 0.906%

    No Known Activations