© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143080
    Prev
    Next
    INDEX
    Explanations

    response: "Да" followed by verbs or phrases

    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_0_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
    ת
    1.97
    Т
    1.59
    я
    1.53
    ン
    1.50
    The
    1.46
    מ
    1.43
    어
    1.38
    ী
    1.34
     innych
    1.33
    ă
    1.33
    POSITIVE LOGITS
    to
    1.52
    くちゃ
    1.35
    s
    1.27
    та
    1.24
    τή
    1.23
    ん
    1.23
    ll
    1.22
    land
    1.20
    have
    1.17
    ับ
    1.14
    Activations Density 0.000%

    No Known Activations