© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199094
    Prev
    Next
    INDEX
    Explanations

    finding or discovery

    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_27_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
     overshadow
    0.43
    create
    0.41
    避
    0.37
    太过
    0.37
     makeover
    0.36
     prolong
    0.36
    当初
    0.36
    increases
    0.36
    避け
    0.35
     create
    0.34
    POSITIVE LOGITS
     atentos
    0.44
     পরীক্ষা
    0.42
    samples
    0.41
    瀋
    0.41
     अनुसंधान
    0.40
     ಚಿ
    0.40
     Lit
    0.39
     சுமார்
    0.39
    ர்களும்
    0.39
     Affairs
    0.39
    Activations Density 0.002%

    No Known Activations