© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84831
    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_23_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
     hers
    0.50
     itemName
    0.46
     చే
    0.45
     finalText
    0.45
    Τ
    0.45
    श
    0.45
    మ
    0.45
    ELLE
    0.44
    บ
    0.44
     ונ
    0.44
    POSITIVE LOGITS
    oncesto
    0.56
    aguan
    0.54
    apping
    0.48
    tobago
    0.47
    about
    0.46
    nosis
    0.46
    africa
    0.45
    combine
    0.45
     Precip
    0.44
    ató
    0.44
    Activations Density 0.000%

    No Known Activations