© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 135090
    Prev
    Next
    INDEX
    Explanations

    io, ps before punctuation or text

    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_6_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
    ado
    0.88
    are
    0.84
    ية
    0.83
    ०
    0.80
    ある
    0.79
    \%$
    0.79
    </h5>
    0.78
    aya
    0.78
     can
    0.76
    iy
    0.76
    POSITIVE LOGITS
    ľov
    0.82
     degraded
    0.75
    ジ
    0.75
    ின்
    0.74
    ্টেন
    0.74
    蓥
    0.74
     također
    0.73
    Компания
    0.73
     sacré
    0.72
    <
    0.72
    Activations Density 0.000%

    No Known Activations