© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45967
    Prev
    Next
    INDEX
    Explanations

    future and later 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_22_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
    叼
    0.12
     неот
    0.11
     purported
    0.11
     fundamentales
    0.10
     Paryayvachi
    0.10
    魟
    0.10
     草
    0.10
     Расійскай
    0.10
    迺
    0.10
    CharArray
    0.10
    POSITIVE LOGITS
    gg
    0.13
    ogg
    0.12
    <0xB8>
    0.11
    徹底
    0.11
    psi
    0.11
    cr
    0.11
    pp
    0.11
    ps
    0.11
    psych
    0.11
    intera
    0.11
    Activations Density 0.031%

    No Known Activations