© 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. 45670
    Prev
    Next
    INDEX
    Explanations

    database connection and client initialization

    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
    拿出
    0.20
    漃
    0.19
    utiliser
    0.19
     flaw
    0.18
     '@/
    0.18
    നാ
    0.18
    னவே
    0.18
     ischa
    0.18
    ಾದರೆ
    0.18
    मानुसार
    0.18
    POSITIVE LOGITS
    ↵↵
    0.20
     and
    0.19
     frug
    0.19
     Opie
    0.19
     New
    0.19
     —
    0.19
     appraisals
    0.19
     seated
    0.19
     Roles
    0.19
     Any
    0.19
    Activations Density 0.001%

    No Known Activations