© 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. 89908
    Prev
    Next
    INDEX
    Explanations

    Autom

    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
    '
    1.13
    0.68
    ’
    0.66
     pueda
    0.61
     discret
    0.60
     primaria
    0.59
    ى
    0.58
     pretende
    0.57
     reliant
    0.57
     semblable
    0.57
    POSITIVE LOGITS
    W
    0.82
    و
    0.82
    N
    0.77
    0
    0.74
    I
    0.73
    D
    0.68
    ps
    0.67
    market
    0.67
    name
    0.67
    model
    0.66
    Activations Density 0.001%

    No Known Activations