© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 154398
    Prev
    Next
    INDEX
    Explanations

    smooth skin

    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_60_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
     cultured
    0.49
    த்த
    0.46
    ють
    0.44
    荩
    0.44
    Raising
    0.44
     cultivated
    0.44
    اتي
    0.41
    棫
    0.40
     ممكن
    0.40
    Kết
    0.40
    POSITIVE LOGITS
     de
    0.67
     sat
    0.55
    sat
    0.48
     disruption
    0.48
    Sat
    0.47
     interruption
    0.44
     breakage
    0.43
     decontamination
    0.43
     thrown
    0.43
     cardiac
    0.43
    Activations Density 0.003%

    No Known Activations