© 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. 123388
    Prev
    Next
    INDEX
    Explanations

    establishes

    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
    the
    0.84
     It
    0.81
    tion
    0.81
    ł
    0.77
    tumor
    0.73
    tn
    0.71
    л
    0.70
     it
    0.70
    め
    0.68
    t
    0.67
    POSITIVE LOGITS
    ’
    0.99
    ి
    0.81
    ́c
    0.78
    '
    0.77
    és
    0.76
    ă
    0.72
    அ
    0.71
     Bagn
    0.70
    b
    0.70
     that
    0.68
    Activations Density 0.000%

    No Known Activations