© 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. 5107
    Prev
    Next
    INDEX
    Explanations

    source of

    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
    ਉ
    1.96
    ओ
    1.95
    शुदा
    1.93
    ie
    1.92
    ‍
    1.90
    ך
    1.88
    小
    1.87
    Tabla
    1.78
    ່ນ
    1.77
     alku
    1.76
    POSITIVE LOGITS
    ר
    2.70
    ل
    2.17
    স্থানীয়
    2.13
    পাত্র
    2.05
    স্থানীয়
    2.04
     Daya
    1.92
    不断的
    1.89
     $("#
    1.89
    enamefont
    1.86
    लिस
    1.84
    Activations Density 0.083%

    No Known Activations