© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80915
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_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
    >[
    0.44
     വൈദ്യ
    0.40
     >,
    0.38
    apace
    0.37
     촉
    0.37
    වි
    0.36
    traditional
    0.36
     clinically
    0.36
    ]._
    0.36
     ľ
    0.35
    POSITIVE LOGITS
    Bound
    0.36
    ClassObject
    0.36
     quelle
    0.35
     એ
    0.34
     tekint
    0.34
    Credit
    0.34
     multiplier
    0.34
    estamps
    0.34
     Credit
    0.34
    сын
    0.34
    Activations Density 0.000%

    No Known Activations