© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 210987
    Prev
    Next
    INDEX
    Explanations

    7

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_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
    ੫
    0.50
    챠
    0.44
     Hongkong
    0.40
     vijf
    0.40
    emens
    0.40
     chimie
    0.38
     ५
    0.38
    את
    0.38
     fins
    0.37
     পাচ
    0.37
    POSITIVE LOGITS
    Maintenance
    0.39
    paran
    0.39
    spent
    0.36
    側
    0.35
     Maintenance
    0.35
    bank
    0.35
    Ten
    0.35
     trọng
    0.34
    Aud
    0.34
     Ten
    0.33
    Activations Density 0.000%

    No Known Activations