© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 5177
    Prev
    Next
    INDEX
    Explanations

    /

    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_44_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
    Beacon
    0.37
     Beacon
    0.37
     defeats
    0.35
     beacon
    0.34
    💅
    0.34
    tw
    0.33
    HEAP
    0.33
     forment
    0.32
    forEach
    0.32
    hiv
    0.32
    POSITIVE LOGITS
     fflush
    0.40
     tiga
    0.38
     tact
    0.36
     cass
    0.35
    ❸
    0.35
    임을
    0.35
     ym
    0.35
     энцикло
    0.35
     insulting
    0.34
    ित
    0.34
    Activations Density 0.000%

    No Known Activations