© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33195
    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_40_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
     сер
    0.42
    horn
    0.40
     রাখ
    0.39
    僳
    0.38
     ser
    0.37
    stag
    0.36
    ันท
    0.36
     Miss
    0.36
     سر
    0.36
     CPC
    0.36
    POSITIVE LOGITS
     procedures
    0.42
     blocks
    0.42
    procedures
    0.38
    createComponent
    0.38
     Locks
    0.38
     component
    0.38
    uzzy
    0.38
    銷
    0.37
    ριά
    0.37
    メリカ
    0.37
    Activations Density 0.036%

    No Known Activations