© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 81819
    Prev
    Next
    INDEX
    Explanations

    instructions

    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_29_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
     حوالے
    0.33
     вле
    0.32
     Percentage
    0.32
     मकान
    0.32
     Filled
    0.32
     \%,
    0.31
    ="")
    0.31
     Stack
    0.30
     விரு
    0.30
     Start
    0.30
    POSITIVE LOGITS
    不過
    0.35
     ɖ
    0.33
    ␣
    0.32
    abd
    0.31
    ybės
    0.31
    ́c
    0.30
    arif
    0.30
    ᑐ
    0.30
     europäischen
    0.29
     infinito
    0.29
    Activations Density 0.076%

    No Known Activations