© 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. 5455
    Prev
    Next
    INDEX
    Explanations

    new st, Louboutin, room names, justice.gov

    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
    $&$
    1.03
     demethyl
    0.96
    isEqualTo
    0.94
     تعالى
    0.92
     divorced
    0.89
     Mathf
    0.88
     dificuldades
    0.87
    ${\
    0.86
    TouchableOpacity
    0.86
     तरह
    0.86
    POSITIVE LOGITS
    y
    1.02
    ch
    0.98
    i
    0.97
    ाइड
    0.92
    能
    0.86
    is
    0.86
    e
    0.86
    ن
    0.82
    छ
    0.82
    or
    0.79
    Activations Density 0.001%

    No Known Activations