© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 180015
    Prev
    Next
    INDEX
    Explanations

    lists starting with `Can`

    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_24_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
    E
    0.55
    H
    0.47
     MEAS
    0.47
    ER
    0.46
    I
    0.46
    O
    0.45
    L
    0.44
    Measurements
    0.43
    IES
    0.42
    CCC
    0.42
    POSITIVE LOGITS
    supported
    0.49
    柯
    0.49
    getCql
    0.48
    parse
    0.47
    ichtigung
    0.47
    transformer
    0.46
    س
    0.45
     bact
    0.44
    ਲੀ
    0.44
    مد
    0.44
    Activations Density 0.000%

    No Known Activations