© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162016
    Prev
    Next
    INDEX
    Explanations

    the "must-haves"

    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_2_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
    ні
    1.41
    ش
    1.33
    ва
    1.26
    ي
    1.22
    ни
    1.20
    ু
    1.20
    ет
    1.19
    ា
    1.14
    ции
    1.11
    دي
    1.11
    POSITIVE LOGITS
    ED
    1.83
    F
    1.77
    S
    1.67
    H
    1.49
    J
    1.45
    AF
    1.44
    OR
    1.38
    ACT
    1.34
    E
    1.34
    AST
    1.33
    Activations Density 0.000%

    No Known Activations