© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258430
    Prev
    Next
    INDEX
    Explanations

    multiple exclamation marks

    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_22_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
     storica
    0.47
    ফোঁ
    0.44
     Freeport
    0.44
     historische
    0.43
     तीर
    0.43
    slideDuplicate
    0.43
    ᴺ
    0.43
     inputRange
    0.42
    鲮
    0.42
    etor
    0.41
    POSITIVE LOGITS
     !
    0.45
     نحن
    0.40
     !!
    0.40
     &
    0.38
     हमने
    0.38
     />
    0.38
    onać
    0.37
     !!!
    0.37
    ↵
    0.36
    ತ್ರಿ
    0.36
    Activations Density 0.007%

    No Known Activations