© 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. 13155
    Prev
    Next
    INDEX
    Explanations

    the phrase "a long way" (and variants with "step")

    oai_token-act-pair · gemini-2.0-flash

    Distances

    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
    例文帳に追加
    -0.73
    ⓧ
    -0.68
    исленность
    -0.65
    ituary
    -0.65
    sidemargin
    -0.61
    ///</
    -0.60
    ագրություններ
    -0.59
    קישורים
    -0.59
    scription
    -0.58
     correctes
    -0.58
    POSITIVE LOGITS
    oa̍t
    0.60
     scattata
    0.48
     artistique
    0.46
    ysty
    0.45
     morire
    0.45
    yonel
    0.42
     pasaron
    0.41
     waveguide
    0.40
     carbonates
    0.40
    withIdentifier
    0.40
    Activations Density 1.558%

    No Known Activations