© 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. 5197
    Prev
    Next
    INDEX
    Explanations

    during or after states

    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
    el
    2.38
    at
    2.14
    as
    2.03
     fibrous
    1.98
    anil
    1.97
    𝖽
    1.94
    asr
    1.91
    ം
    1.89
     SVM
    1.88
     czyli
    1.86
    POSITIVE LOGITS
    то
    2.51
    tım
    2.24
     pasti
    1.99
    透過
    1.97
    öglichkeiten
    1.85
    х
    1.85
     rakyat
    1.85
    هم
    1.82
    नर
    1.82
     goreng
    1.82
    Activations Density 0.060%

    No Known Activations