© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209994
    Prev
    Next
    INDEX
    Explanations

    frankly, followed by a comma

    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_10_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
     *
    0.73
     negativa
    0.70
    able
    0.67
     alternative
    0.67
    ue
    0.67
    ess
    0.66
     ROW
    0.66
     expenditure
    0.65
     identifiable
    0.65
    emos
    0.65
    POSITIVE LOGITS
    '
    0.91
    ’
    0.90
     ましょう
    0.82
    ‵
    0.78
     दट
    0.77
    𝓰
    0.75
    し
    0.75
    ৫
    0.75
    ໃຊ້
    0.73
    ぬい
    0.72
    Activations Density 0.001%

    No Known Activations