© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 206940
    Prev
    Next
    INDEX
    Explanations

    insertion into

    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_20_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
     closed
    0.44
    aruh
    0.42
     azione
    0.42
    诮
    0.42
    ुलिस
    0.41
     信息
    0.41
     prostagland
    0.41
    插入
    0.40
    croll
    0.40
     要素
    0.40
    POSITIVE LOGITS
    og
    0.38
    ly
    0.38
    adio
    0.38
    q
    0.37
    lop
    0.37
    uzioni
    0.37
    endsWith
    0.37
    age
    0.37
    "):
    0.37
    ကြီး
    0.36
    Activations Density 0.002%

    No Known Activations