© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204667
    Prev
    Next
    INDEX
    Explanations

    import Dataset/DataLoader

    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_25_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
     tới
    0.42
    ి
    0.42
     полную
    0.41
    த்துறை
    0.41
    出的
    0.41
     полной
    0.41
     fortemente
    0.40
     सितारों
    0.40
     Conde
    0.39
    为
    0.39
    POSITIVE LOGITS
    }($
    0.41
    coran
    0.41
    𝓸
    0.38
    backgroundSplit
    0.38
    cheid
    0.37
    ベビー
    0.37
    insuff
    0.37
     damn
    0.35
    bestand
    0.35
    kaz
    0.35
    Activations Density 0.000%

    No Known Activations