© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 50104
    Prev
    Next
    INDEX
    Explanations

    numbers and data

    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
    0
    0.43
    деся
    0.42
     novel
    0.39
    десят
    0.39
    4
    0.37
     puluh
    0.36
    3
    0.36
     <%=
    0.36
    ટે
    0.35
    Novel
    0.35
    POSITIVE LOGITS
     Slow
    0.37
     Lun
    0.37
     Affairs
    0.37
    のも
    0.36
     Uch
    0.35
     Lur
    0.35
    ാനം
    0.35
     Straf
    0.35
    сный
    0.34
     የግ
    0.34
    Activations Density 0.043%

    No Known Activations