© 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
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36382
    Prev
    Next
    INDEX
    Explanations

    National Institute of Standards and Technology

    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_3_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
    ب
    0.99
    '}
    0.89
    G
    0.79
     ك
    0.68
    }.\
    0.66
     be
    0.65
     Ét
    0.64
    }).
    0.63
    P
    0.63
     i
    0.63
    POSITIVE LOGITS
    o
    0.82
    d
    0.79
    ed
    0.75
    ется
    0.69
    리
    0.66
    ul
    0.60
    uating
    0.57
    kts
    0.57
    maligngroup
    0.56
    क्की
    0.56
    Activations Density 0.000%

    No Known Activations