© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 202416
    Prev
    Next
    INDEX
    Explanations

    buoyancy

    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_12_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
    ן
    0.51
     allocated
    0.49
    ב
    0.49
     değeri
    0.48
    х
    0.48
    ﻟ
    0.47
    錘
    0.46
     allocating
    0.46
    ἱ
    0.46
    LLER
    0.46
    POSITIVE LOGITS
    yana
    0.49
    uña
    0.47
    Fluent
    0.45
    adors
    0.45
    gebiet
    0.44
    aba
    0.44
    scan
    0.44
    üsseldorf
    0.44
    вары
    0.44
     அங்கு
    0.43
    Activations Density 0.000%

    No Known Activations