© 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. 133479
    Prev
    Next
    INDEX
    Explanations

    9-10

    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
     are
    0.89
    3
    0.89
    4
    0.87
    9
    0.86
    5
    0.78
    স
    0.77
     it
    0.76
     są
    0.76
    6
    0.76
    7
    0.76
    POSITIVE LOGITS
    ور
    0.88
    εν
    0.75
    ων
    0.74
    és
    0.69
    w
    0.69
    р
    0.69
    mprj
    0.68
    ments
    0.66
    v
    0.66
    aigne
    0.66
    Activations Density 0.001%

    No Known Activations