© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6275
    Prev
    Next
    INDEX
    Explanations

    something more or akin

    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_39_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
    astanza
    0.34
    菜
    0.32
     lipoproteins
    0.30
    Sink
    0.30
    サイズの
    0.29
     주장
    0.29
    ದಿ
    0.29
     thẻ
    0.29
    Credential
    0.28
    憶
    0.28
    POSITIVE LOGITS
     onlook
    0.38
     observers
    0.37
     nyata
    0.34
    observer
    0.34
     seismic
    0.34
     kaybed
    0.33
     observer
    0.33
     नेपाल
    0.33
     ephemeral
    0.33
     onlookers
    0.32
    Activations Density 0.055%

    No Known Activations