© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104731
    Prev
    Next
    INDEX
    Explanations

    'ació constant', 'ació personal'

    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_1_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
     at
    1.54
     for
    1.53
    ר
    1.49
    ל
    1.32
    p
    1.25
    l
    1.24
    m
    1.23
    ل
    1.14
     by
    1.13
    Z
    1.13
    POSITIVE LOGITS
    \
    1.13
     valida
    1.04
     μόνο
    1.00
    ää
    0.96
    ，
    0.95
    ный
    0.93
    นั้น
    0.93
    ,
    0.91
    的
    0.91
    ↵↵
    0.91
    Activations Density 0.001%

    No Known Activations