© 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. 138314
    Prev
    Next
    INDEX
    Explanations

    diamond

    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
    AM
    0.42
    
    0.40
     stronger
    0.38
    ahre
    0.38
     setae
    0.38
    kirche
    0.38
     vanes
    0.38
    Liens
    0.38
    вам
    0.38
     flanks
    0.38
    POSITIVE LOGITS
     derrot
    0.41
     Embora
    0.41
    ']}
    0.39
    ෙස
    0.38
    }\
    0.38
     Durante
    0.38
     diciendo
    0.38
    ль
    0.38
    fclose
    0.37
    achery
    0.37
    Activations Density 0.000%

    No Known Activations