© 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. 89332
    Prev
    Next
    INDEX
    Explanations

    filler words

    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
    έρα
    0.42
    r
    0.40
    senior
    0.38
    upra
    0.37
    lacht
    0.37
     চ্যানে
    0.37
    bonded
    0.37
    вания
    0.36
     TCS
    0.36
    чению
    0.35
    POSITIVE LOGITS
     um
    0.99
    有
    0.89
    でも
    0.89
    에서도
    0.71
    Um
    0.61
     Um
    0.59
     でも
    0.57
    ίκ
    0.56
    มี
    0.53
     uh
    0.50
    Activations Density 0.007%

    No Known Activations