© 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. 215645
    Prev
    Next
    INDEX
    Explanations

    x, width assignment

    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_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
     Sank
    0.37
     Bor
    0.34
     Franc
    0.33
    bor
    0.33
    rho
    0.32
     Saw
    0.32
    jk
    0.32
     ७
    0.32
     Pollution
    0.32
     Roger
    0.32
    POSITIVE LOGITS
     coûts
    0.36
    󠁳
    0.35
    یر
    0.35
    повід
    0.34
     revenus
    0.33
    Costs
    0.33
     stratégies
    0.33
    碖
    0.33
    পশ্চিম
    0.32
     COSTS
    0.32
    Activations Density 0.000%

    No Known Activations