© 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. 219625
    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
     સંદ
    0.40
     উপমহাদেশের
    0.40
    joen
    0.37
     আহমে
    0.37
     Bonnet
    0.36
    🏔
    0.36
     তহ
    0.36
     食器
    0.36
    काने
    0.36
    戻
    0.36
    POSITIVE LOGITS
     Cl
    0.46
     collapsing
    0.41
    ってくる
    0.40
     works
    0.40
     can
    0.40
     isa
    0.40
    dro
    0.39
     coco
    0.38
     computes
    0.38
     single
    0.37
    Activations Density 0.000%

    No Known Activations