© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199821
    Prev
    Next
    INDEX
    Explanations

    allows performing actions

    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_12_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
    W
    0.65
    ;\
    0.64
    P
    0.64
    V
    0.64
    AS
    0.58
     Nhưng
    0.58
    ASM
    0.57
    bP
    0.55
    AVE
    0.55
     pointB
    0.55
    POSITIVE LOGITS
     is
    0.63
     idé
    0.58
    isation
    0.54
     Ment
    0.54
    ก
    0.54
    ipped
    0.53
    umis
    0.53
    ية
    0.53
    izers
    0.52
    encies
    0.52
    Activations Density 0.000%

    No Known Activations