© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248485
    Prev
    Next
    INDEX
    Explanations

    ear

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     very
    1.84
    Very
    1.66
    很
    1.58
    very
    1.57
     Very
    1.55
     très
    1.55
     очень
    1.55
     sehr
    1.45
     rất
    1.45
     muy
    1.42
    POSITIVE LOGITS
     مب
    1.38
     المب
    1.32
     일
    1.16
    arly
    0.91
     mb
    0.75
    일
    0.72
     MB
    0.65
    mb
    0.65
    ariy
    0.63
    aly
    0.63
    Activations Density 0.002%

    No Known Activations