© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45344
    Prev
    Next
    INDEX
    Explanations

    mana cost or curve

    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_13_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
    ^{\
    0.12
    ^{
    0.11
    ubuntu
    0.10
    _
    0.09
    op
    0.09
    action
    0.09
    ОВ
    0.09
    attribute
    0.09
    uration
    0.09
    order
    0.08
    POSITIVE LOGITS
     parada
    0.10
    ﺝ
    0.10
     migli
    0.10
     cela
    0.10
     frivol
    0.09
     дож
    0.09
     えっと
    0.09
     შორის
    0.09
     Moris
    0.09
     kilom
    0.09
    Activations Density 0.003%

    No Known Activations