© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4708
    Prev
    Next
    INDEX
    Explanations

    words that are related to measurements and sizes as well as words that describe relative change

    oai_token-act-pair · gemini-2.0-flash

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    nader
    -0.50
     rodea
    -0.49
    лык
    -0.48
     mại
    -0.47
     guste
    -0.46
    ulkner
    -0.45
    ációs
    -0.45
    HasOne
    -0.44
    moiselle
    -0.44
    UBLE
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.80
     TextInputType
    0.76
    CodeAttribute
    0.72
    Xna
    0.71
    UIControlState
    0.71
    GraphicsUnit
    0.69
    principalColumn
    0.68
    ActionCreators
    0.66
     GoogleFonts
    0.65
    styleUrls
    0.64
    Activations Density 2.740%

    No Known Activations