© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248605
    Prev
    Next
    INDEX
    Explanations

    text processing

    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_56_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
     recharged
    0.40
     megap
    0.37
    CLASSI
    0.36
    Reuters
    0.36
    एसआई
    0.36
    氢
    0.36
    SEE
    0.35
     amort
    0.35
     tremendously
    0.35
    প
    0.35
    POSITIVE LOGITS
    ٥
    0.42
     extends
    0.41
    }=(\
    0.40
     مذہ
    0.39
    ;*/
    0.38
     Panel
    0.38
    _;
    0.38
     যাও
    0.38
    ితో
    0.38
    ForThe
    0.38
    Activations Density 0.003%

    No Known Activations