© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93164
    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_11_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
    in
    0.65
    c
    0.58
    h
    0.57
    miktar
    0.52
    pathi
    0.50
     ocurren
    0.49
    g
    0.48
     były
    0.47
    sı
    0.47
    lą
    0.47
    POSITIVE LOGITS
    2
    0.53
     ACH
    0.53
    ني
    0.48
     BBS
    0.46
     IAM
    0.44
     US
    0.44
     cultured
    0.43
     IDENT
    0.43
     Ita
    0.43
     Allianz
    0.42
    Activations Density 0.000%

    No Known Activations