© 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. 3569
    Prev
    Next
    INDEX
    Explanations

    overfit, reciprocating, interrogatories, застрелення, impulse, über, clogged

    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
    0
    0.54
    esque
    0.52
    puede
    0.52
    2
    0.52
    wide
    0.52
     acre
    0.51
    may
    0.50
    mith
    0.50
    GPIO
    0.49
     byť
    0.49
    POSITIVE LOGITS
    iting
    0.57
    ❽
    0.54
    ppings
    0.52
    𝒅
    0.52
    𝑨
    0.51
    inate
    0.51
    uted
    0.51
    ig
    0.51
    𝑭
    0.50
     Prestige
    0.49
    Activations Density 0.384%

    No Known Activations