© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215598
    Prev
    Next
    INDEX
    Explanations

    badness

    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_5_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
    0
    1.18
    9
    1.09
    5
    1.02
    profits
    0.98
     indiquer
    0.95
    ނ
    0.94
    4
    0.93
    пки
    0.93
    A
    0.93
     товары
    0.92
    POSITIVE LOGITS
    д
    1.15
    د
    1.10
    ך
    1.04
     it
    1.00
    z
    1.00
     می
    0.97
     doctorate
    0.96
    ū
    0.94
     lost
    0.93
     president
    0.93
    Activations Density 0.000%

    No Known Activations