© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 104051
    Prev
    Next
    INDEX
    Explanations

    ability

    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_1_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
    л
    1.07
    ם
    1.06
    t
    1.05
     که
    1.02
    ר
    1.01
    б
    0.99
    ル
    0.96
    tabname
    0.91
    propertyName
    0.90
    instrList
    0.89
    POSITIVE LOGITS
    x
    1.65
    y
    1.54
    re
    1.34
    od
    1.33
    ed
    1.29
    orna
    1.27
    of
    1.26
     l
    1.24
    n
    1.23
    and
    1.17
    Activations Density 0.003%

    No Known Activations