© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15620
    Prev
    Next
    INDEX
    Explanations

    yet to be

    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_40_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
    Binary
    0.37
     going
    0.36
    सो
    0.36
    敨
    0.35
    絲
    0.35
    യില്ല
    0.35
    ണ
    0.34
    ர்த்த
    0.34
    ="./
    0.34
    going
    0.34
    POSITIVE LOGITS
     yet
    2.52
     Yet
    2.17
    Yet
    2.08
    yet
    1.99
     ännu
    1.75
     jeszcze
    1.59
     еще
    1.54
     noch
    1.50
     belum
    1.47
    尚未
    1.46
    Activations Density 0.040%

    No Known Activations