© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160518
    Prev
    Next
    INDEX
    Explanations

    resembling

    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_2_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
    ای
    1.23
    I
    1.21
     as
    1.13
    ک
    1.13
     モ
    1.11
     جنوبی
    1.10
     coba
    1.02
    one
    1.01
    انی
    0.95
    یل
    0.93
    POSITIVE LOGITS
    -
    1.45
    ية
    1.38
    га
    1.24
    '
    1.24
    ة
    1.18
    ০
    1.15
    н
    1.08
    ные
    1.05
     влия
    1.05
    ции
    1.04
    Activations Density 0.000%

    No Known Activations