© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 146002
    Prev
    Next
    INDEX
    Explanations

    affected by

    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_0_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
    1.43
    おく
    1.38
    お
    1.36
    りは
    1.34
    ৩
    1.31
    となる
    1.21
    든
    1.21
    おお
    1.20
    ी
    1.20
    .
    1.20
    POSITIVE LOGITS
    us
    1.66
     I
    1.50
    od
    1.42
     it
    1.30
    та
    1.30
    ج
    1.27
    ia
    1.26
     you
    1.20
    ing
    1.16
    ॉन
    1.15
    Activations Density 0.000%

    No Known Activations