© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 195569
    Prev
    Next
    INDEX
    Explanations

    specific items

    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_50_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
    חה
    0.38
     午
    0.38
    Flat
    0.38
    olfo
    0.38
     सत
    0.37
    lui
    0.37
     Roi
    0.37
    Marg
    0.36
     Flat
    0.35
    वण
    0.35
    POSITIVE LOGITS
     Тя
    0.43
     Twe
    0.42
    lement
    0.40
     Lemb
    0.40
    ார்க்க
    0.40
    蕨
    0.38
     twe
    0.38
    ]],
    0.38
     threx
    0.38
    TrackedDevice
    0.38
    Activations Density 0.002%

    No Known Activations