© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106947
    Prev
    Next
    INDEX
    Explanations

    variable declaration `int n`

    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
    s
    1.19
    ;
    1.15
    ۔
    1.14
    3
    1.13
    0
    1.12
    .
    1.10
    ę
    1.05
    ों
    1.04
    ات
    1.03
    ми
    1.02
    POSITIVE LOGITS
    c
    1.14
    ור
    1.11
    ’
    1.05
     doesn
    1.04
     can
    0.96
     hasn
    0.96
     He
    0.96
     comenc
    0.94
     aggravate
    0.91
     they
    0.88
    Activations Density 0.000%

    No Known Activations