© 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. 91375
    Prev
    Next
    INDEX
    Explanations

    ap followed by iano

    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
    ى
    0.69
    </h2>
    0.61
    い
    0.59
    น
    0.57
    お問い合わせ
    0.57
    取り付け
    0.57
    ות
    0.56
    ต์
    0.56
    </sup>
    0.55
    が高い
    0.55
    POSITIVE LOGITS
    and
    0.93
    ap
    0.80
    it
    0.79
    områ
    0.77
    ités
    0.77
    ال
    0.76
    itä
    0.76
    ol
    0.74
    ar
    0.72
    ud
    0.72
    Activations Density 0.000%

    No Known Activations