© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48813
    Prev
    Next
    INDEX
    Explanations

    how much cost average

    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_31_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
     atof
    0.36
    ologisch
    0.34
     differs
    0.33
     metabolites
    0.33
     postulates
    0.32
     underlines
    0.32
     }]);
    0.31
    buscador
    0.31
     считаю
    0.31
    ଞ
    0.31
    POSITIVE LOGITS
     AVERAGE
    0.35
    èse
    0.34
     promedio
    0.34
    average
    0.34
    Naming
    0.33
    Average
    0.32
     работ
    0.32
     табле
    0.32
    Bu
    0.32
     Average
    0.32
    Activations Density 0.009%

    No Known Activations