© 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-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 261261
    Prev
    Next
    INDEX
    Explanations

    stepper motor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    на
    0.98
    ната
    0.91
    он
    0.83
    ع
    0.77
    ش
    0.70
    وم
    0.69
    ى
    0.69
    ла
    0.68
    0.68
    會有
    0.66
    POSITIVE LOGITS
    in
    1.53
    )
    0.95
    er
    0.95
    s
    0.93
     I
    0.89
    ]
    0.85
    o
    0.83
    :
    0.80
    ;
    0.80
    i
    0.79
    Activations Density 0.000%

    No Known Activations