© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3627
    Prev
    Next
    INDEX
    Explanations

    the article + noun

    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_5_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
     reforestation
    0.61
    е
    0.58
     Faites
    0.54
     benzo
    0.53
     malaysia
    0.53
    S
    0.52
     vitro
    0.52
     roz
    0.52
     annan
    0.51
    Ρ
    0.50
    POSITIVE LOGITS
    jenigen
    0.60
    mselves
    0.54
    ophylline
    0.53
    هم
    0.52
    ণের
    0.51
    駅から
    0.48
    次数
    0.48
    $-\
    0.48
    وح
    0.48
    েন
    0.46
    Activations Density 0.524%

    No Known Activations