© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 230405
    Prev
    Next
    INDEX
    Explanations

    outcome of

    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_6_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
    س
    1.41
    с
    1.32
    á
    1.20
    ä
    1.12
    ス
    0.96
    नी
    0.95
    è
    0.92
    و
    0.91
    ą
    0.91
    udah
    0.90
    POSITIVE LOGITS
     perso
    0.97
     altre
    0.84
     domicilio
    0.84
     okaza
    0.84
    U
    0.84
     il
    0.83
     puoi
    0.82
     encont
    0.81
     apoio
    0.80
     projek
    0.79
    Activations Density 0.001%

    No Known Activations