© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 18644
    Prev
    Next
    INDEX
    Explanations

    want to know

    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_15_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
    .)
    0.15
    ↵
    0.15
    :
    0.15
    ;
    0.15
    ↵↵
    0.14
    ă
    0.14
    ,
    0.14
     horizontal
    0.14
     manifestation
    0.13
     Javascript
    0.13
    POSITIVE LOGITS
    发展的
    0.15
     clockRadius
    0.13
     deixe
    0.13
     अफेयर्स
    0.12
    <0x06>
    0.12
     ಚಿ
    0.12
     colorChoice
    0.12
     miscon
    0.12
     huevo
    0.12
     fillColorSpace
    0.12
    Activations Density 0.008%

    No Known Activations