© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4136
    Prev
    Next
    INDEX
    Explanations

    the word "age" and a couple of uses of the word "tank."

    oai_token-act-pair · gemini-2.0-flash

    Young age or liquid containers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     plufieurs
    -1.18
     feroit
    -1.17
    <bos>
    -1.17
     Efq
    -1.14
     avoient
    -1.13
     ainfi
    -1.13
     définiti
    -1.06
     quelcon
    -1.03
    +:+
    -1.02
    adaptiveStyles
    -1.02
    POSITIVE LOGITS
    ,
    0.72
     de
    0.70
     el
    0.66
     (
    0.63
    .
    0.60
     re
    0.56
     ar
    0.55
    C
    0.55
     fre
    0.55
     die
    0.55
    Activations Density 0.373%

    No Known Activations