© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 203812
    Prev
    Next
    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_25_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
     integrado
    0.36
    mea
    0.35
     રહ્યા
    0.35
    उनके
    0.35
    鍚
    0.34
     цієї
    0.34
    或其他
    0.34
    盱
    0.34
    苖
    0.34
    েরি
    0.33
    POSITIVE LOGITS
     vscode
    0.45
     পাবে
    0.40
    important
    0.37
    seekers
    0.37
     دور
    0.36
     شن
    0.35
     distort
    0.34
     preempt
    0.34
     stra
    0.33
     producen
    0.33
    Activations Density 0.002%

    No Known Activations