© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 166099
    Prev
    Next
    INDEX
    Explanations

    primary key definitions

    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_34_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
     disamb
    0.42
     तिलक
    0.39
     loosening
    0.38
     [],
    0.37
     கேட்க
    0.37
    <0x91>
    0.37
     (*)
    0.36
     આજ
    0.36
     lanç
    0.36
    राय
    0.36
    POSITIVE LOGITS
     Schall
    0.46
    putable
    0.38
     GRAM
    0.38
    Fort
    0.37
    transmitted
    0.36
     transmitted
    0.36
     waterfall
    0.36
     Hota
    0.35
    Eva
    0.35
     heats
    0.35
    Activations Density 0.001%

    No Known Activations