© 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. 14683
    Prev
    Next
    INDEX
    Explanations

    the words relating to fixing bicycles plus a recipe

    oai_token-act-pair · gemini-2.0-flash

    Cleaning and coating

    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
     يتيمه
    -0.70
    NegativeButton
    -0.66
     typelib
    -0.66
    providedIn
    -0.63
     Turn
    -0.60
     femininos
    -0.59
     Conſ
    -0.58
    AutoScaleMode
    -0.58
    Referencie
    -0.57
    utenant
    -0.56
    POSITIVE LOGITS
    numerusform
    0.45
    brev
    0.44
    FDRE
    0.42
    prey
    0.41
     resum
    0.40
    RenderAtEndOf
    0.39
    [](
    0.39
    Mais
    0.39
    runt
    0.38
    (/[
    0.38
    Activations Density 1.850%

    No Known Activations