© 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. 134348
    Prev
    Next
    INDEX
    Explanations

    `from` followed by context words

    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
    ’
    1.15
    n
    1.03
    ta
    0.96
    <h5>
    0.92
    ’),
    0.91
    ton
    0.86
    ter
    0.83
    qvist
    0.83
    ker
    0.78
    <h3>
    0.78
    POSITIVE LOGITS
    0
    1.04
    ی
    0.94
    ان
    0.84
    ０
    0.84
    ين
    0.84
    هن
    0.84
    лон
    0.84
    .
    0.82
    ג
    0.76
    ции
    0.75
    Activations Density 0.000%

    No Known Activations