© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118939
    Prev
    Next
    INDEX
    Explanations

    library or import statements

    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_27_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
    hkar
    0.47
    трибу
    0.44
    Upgradeable
    0.42
    벳
    0.42
    Escolhido
    0.40
    伥
    0.40
    ͆
    0.39
    اندار
    0.39
     требований
    0.39
     нас
    0.38
    POSITIVE LOGITS
     insults
    0.38
     insult
    0.38
     Mille
    0.31
    雹
    0.31
     परा
    0.31
    umoto
    0.31
     Madison
    0.31
     Disaster
    0.30
     retardation
    0.30
     Supervision
    0.30
    Activations Density 0.000%

    No Known Activations