© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 198777
    Prev
    Next
    INDEX
    Explanations

    problem

    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_46_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
     loin
    0.40
    umbing
    0.39
     быстро
    0.38
    እን
    0.38
    кс
    0.38
     사례
    0.38
    oyant
    0.37
    番
    0.37
    oureux
    0.37
    ⑅
    0.37
    POSITIVE LOGITS
    Origins
    0.42
     Origins
    0.42
     part
    0.39
     importe
    0.38
     origins
    0.37
    definitions
    0.37
    important
    0.36
    highlight
    0.36
     යුතු
    0.36
    affect
    0.35
    Activations Density 0.001%

    No Known Activations