© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46996
    Prev
    Next
    INDEX
    Explanations

    what make of

    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_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
    ە
    1.16
    प्पू
    0.82
     ።
    0.76
    ین
    0.73
    이죠
    0.73
    >(&
    0.73
    ۶
    0.72
    ༥
    0.71
    た
    0.71
    ментів
    0.70
    POSITIVE LOGITS
    '
    1.34
    0.92
     by
    0.79
    ’
    0.79
    <0x0D>
    0.78
    it
    0.73
    yla
    0.73
     GREEN
    0.71
     for
    0.70
     sabor
    0.70
    Activations Density 0.002%

    No Known Activations