© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51089
    Prev
    Next
    INDEX
    Explanations

    celestial numbers

    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_55_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
    maxcdn
    0.45
     ০১
    0.41
     methyl
    0.40
    萸
    0.40
    =`
    0.39
     tacked
    0.38
     १
    0.38
    𒋛
    0.38
     documentaire
    0.38
     huruf
    0.37
    POSITIVE LOGITS
    resulting
    0.40
    倝
    0.40
    Eat
    0.39
     evoking
    0.37
     resulting
    0.36
    Expl
    0.35
    inations
    0.35
     allot
    0.35
    ʻ
    0.34
    reb
    0.34
    Activations Density 0.000%

    No Known Activations