© 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. 10429
    Prev
    Next
    INDEX
    Explanations

    damage and its effects

    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
    :]
    0.19
    installer
    0.17
    analytic
    0.17
    closing
    0.17
    transpose
    0.17
    වල
    0.16
    clarinet
    0.16
    langle
    0.16
    %]
    0.16
    中心的
    0.16
    POSITIVE LOGITS
     prepaid
    0.20
     umat
    0.18
     swan
    0.17
     beberapa
    0.17
     no
    0.17
     act
    0.17
     đen
    0.17
     ventures
    0.17
     feb
    0.16
     energy
    0.16
    Activations Density 0.006%

    No Known Activations