© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 152231
    Prev
    Next
    INDEX
    Explanations

    tic_tac_toe or calculator display

    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_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
     每个
    0.45
    для
    0.42
    ciplinary
    0.42
    heses
    0.41
    每一
    0.41
    }^{+}
    0.40
    htar
    0.40
     }^{+}
    0.39
     marketing
    0.39
     each
    0.39
    POSITIVE LOGITS
    Reli
    0.39
    萫
    0.39
    Im
    0.36
    罣
    0.36
    Solver
    0.36
    яви
    0.35
     conosc
    0.35
     reng
    0.33
    NavigationView
    0.33
    তা
    0.33
    Activations Density 0.003%

    No Known Activations