© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116536
    Prev
    Next
    INDEX
    Explanations

    common words

    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_27_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
    Haha
    0.33
    睍
    0.33
    stam
    0.33
    visor
    0.32
    hi
    0.32
    tsioon
    0.32
    ਫ
    0.32
    stats
    0.32
    security
    0.31
     Kla
    0.31
    POSITIVE LOGITS
     appropriated
    0.32
    凡
    0.32
     расположены
    0.32
     startTime
    0.31
     investigated
    0.31
    莅
    0.31
     unsuccessfully
    0.31
     upset
    0.30
     न्यायालयाने
    0.30
    ступает
    0.30
    Activations Density 0.008%

    No Known Activations