© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 237407
    Prev
    Next
    INDEX
    Explanations

    after code or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
    专项
    0.40
    ଷ
    0.39
    Southern
    0.39
    Primary
    0.38
     marshall
    0.37
    Mutation
    0.36
     Engl
    0.36
     ہوگا۔
    0.36
    Debut
    0.35
    Rg
    0.34
    POSITIVE LOGITS
     εμφ
    0.40
    呷
    0.40
     Salts
    0.39
     aseptic
    0.39
     duplex
    0.38
     asem
    0.38
     Cosm
    0.37
     Cornelius
    0.37
    ἄ
    0.37
     serum
    0.37
    Activations Density 0.000%

    No Known Activations