© 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. 203972
    Prev
    Next
    INDEX
    Explanations

    say "atches" ending

    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
     M
    0.42
    τας
    0.42
     મ
    0.40
     ம
    0.39
     ม
    0.38
    Organization
    0.38
     ਮ
    0.38
     మ
    0.37
    စ်
    0.37
    issons
    0.37
    POSITIVE LOGITS
    avises
    0.38
     встречи
    0.38
     conversations
    0.38
     sores
    0.37
     visits
    0.37
     aged
    0.36
     biệt
    0.36
     žal
    0.35
     tais
    0.35
     fibers
    0.34
    Activations Density 0.000%

    No Known Activations