© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89411
    Prev
    Next
    INDEX
    Explanations

    names or brands

    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
    is
    1.02
    на
    0.94
    าย
    0.70
    ية
    0.66
    ন
    0.65
    AA
    0.64
    isierte
    0.62
    ismer
    0.61
    наў
    0.60
    Č
    0.59
    POSITIVE LOGITS
    '
    0.80
    h
    0.77
     attainment
    0.71
    -
    0.65
    (
    0.63
    ]
    0.63
     hypothes
    0.62
     dicho
    0.62
     synthes
    0.61
     that
    0.59
    Activations Density 0.000%

    No Known Activations