© 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. 126103
    Prev
    Next
    INDEX
    Explanations

    practices, steepness, chip, salad

    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
    ’
    1.07
    g
    0.83
    a
    0.82
    .’
    0.80
    q
    0.79
    )’
    0.69
    ’?
    0.68
    𝕞
    0.68
    ’”
    0.65
    е
    0.65
    POSITIVE LOGITS
    ش
    0.73
    0.63
    ხ
    0.60
    רק
    0.57
    Ла
    0.57
    ）；
    0.57
    valment
    0.57
    jenigen
    0.56
    িম
    0.55
    ിട
    0.55
    Activations Density 0.001%

    No Known Activations