© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97162
    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_14_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
     authorised
    0.60
    URE
    0.56
     מה
    0.55
     لري
    0.55
     leaving
    0.54
     letting
    0.53
     אס
    0.52
     I
    0.52
     MR
    0.51
    ONA
    0.50
    POSITIVE LOGITS
    Modelo
    0.63
    Grupo
    0.60
    식회사
    0.58
    گ
    0.58
    묶
    0.58
    меры
    0.57
    기업
    0.56
    信
    0.56
    وٹی
    0.55
    Agora
    0.54
    Activations Density 0.000%

    No Known Activations