© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15177
    Prev
    Next
    INDEX
    Explanations

    words related to personal electronic devices

    oai_token-act-pair · gemini-2.0-flash

    tech devices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    -1.14
     myſelf
    -1.06
    providedIn
    -1.04
     BoxDecoration
    -1.04
     Efq
    -1.02
    URLException
    -1.00
     Monfieur
    -0.98
     ModelExpression
    -0.97
     uſed
    -0.95
    sizeCache
    -0.94
    POSITIVE LOGITS
     at
    0.47
    .
    0.45
    ka
    0.42
     (
    0.42
     -
    0.42
    set
    0.41
    '
    0.41
     hard
    0.40
    ,
    0.40
    RO
    0.39
    Activations Density 3.042%

    No Known Activations