© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123999
    Prev
    Next
    INDEX
    Explanations

    giving a range or description

    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
    IR
    1.07
    ER
    0.99
    a
    0.92
    </strong>
    0.85
    IC
    0.83
    UG
    0.80
    OS
    0.79
    ’
    0.78
    </h3>
    0.75
    z
    0.74
    POSITIVE LOGITS
    ת
    0.76
    ή
    0.73
    ع
    0.69
    ኔ
    0.66
    Ꮷ
    0.66
    いいね
    0.65
    begin
    0.65
    ை
    0.65
    壕
    0.65
    ྥ
    0.64
    Activations Density 0.014%

    No Known Activations