© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77493
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    Cruise
    0.41
    </i>
    0.39
    Teachers
    0.39
    檛
    0.38
    Microsoft
    0.38
    ින්
    0.38
    ب
    0.38
    Cu
    0.38
    هلا
    0.38
    ted
    0.37
    POSITIVE LOGITS
     animating
    0.44
     isso
    0.43
     indulging
    0.42
     ഇത്
    0.42
     това
    0.41
     dieses
    0.41
     ഇത
    0.41
     bra
    0.40
     ಇದು
    0.40
     tämä
    0.40
    Activations Density 0.003%

    No Known Activations