© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 175020
    Prev
    Next
    INDEX
    Explanations

    Mad Max or John McClane

    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_20_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
    $).
    0.21
    钞
    0.20
    Encoding
    0.20
    งิน
    0.19
    𝙫
    0.19
    ম্
    0.19
     mehrerer
    0.19
    缬
    0.18
     boyunca
    0.18
     многочис
    0.18
    POSITIVE LOGITS
     road
    0.19
     Road
    0.19
    嬪
    0.18
     not
    0.18
     Gus
    0.18
    드가
    0.18
     Oregon
    0.18
    ()
    0.18
     pathophysiology
    0.17
    us
    0.17
    Activations Density 0.002%

    No Known Activations