© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5356
    Prev
    Next
    INDEX
    Explanations

    coding tutorials and probability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ва
    3.10
    an
    2.96
    ал
    2.74
    ン
    2.60
     ponto
    2.56
    ка
    2.53
    न
    2.51
     silam
    2.45
    вам
    2.42
    ie
    2.41
    POSITIVE LOGITS
    $\$
    2.33
    /[\
    2.25
    on
    2.23
     regards
    2.19
    ON
    2.02
     cosines
    2.02
    wght
    1.94
    $$
    1.94
    $(".
    1.92
     consegu
    1.89
    Activations Density 0.000%

    No Known Activations