© 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. 5248
    Prev
    Next
    INDEX
    Explanations

    quoted text

    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
    tım
    0.84
    er
    0.84
    تهم
    0.74
    tied
    0.74
    𝚒
    0.72
    tiny
    0.70
    tip
    0.69
    ी
    0.69
    い
    0.69
    𝒍
    0.68
    POSITIVE LOGITS
     Puis
    0.70
    GLOBALS
    0.67
    जेक्शन
    0.66
    是通过
    0.65
    к
    0.64
    ,"+
    0.64
    "};
    0.64
     topologically
    0.63
     \%$,
    0.62
     causas
    0.62
    Activations Density 0.218%

    No Known Activations