© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26265
    Prev
    Next
    INDEX
    Explanations

    country flags and trophies

    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_10_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
    ,
    0.69
    :
    0.65
    ers
    0.62
    ondi
    0.60
     ​​
    0.56
    …
    0.56
    iny
    0.56
    ening
    0.55
    lant
    0.55
    aney
    0.51
    POSITIVE LOGITS
    UT
    0.55
     যেরূপ
    0.55
    ঢাকার
    0.54
    UF
    0.53
    ssid
    0.52
    Ultr
    0.51
    덱
    0.51
    কিন
    0.51
    ಿಸ್ಟ
    0.50
    帆
    0.50
    Activations Density 0.000%

    No Known Activations