© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39031
    Prev
    Next
    INDEX
    Explanations

    ending eventually

    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_57_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
    hydrocèle
    0.36
     Skipper
    0.33
     functionalities
    0.33
    omeness
    0.33
    คาร
    0.32
    丏
    0.32
    cocks
    0.32
    ྜ
    0.32
     repell
    0.32
     Took
    0.32
    POSITIVE LOGITS
     nak
    2.22
    Nak
    1.85
     Nak
    1.79
    nak
    1.46
     نق
    1.43
     अंत
    1.27
     בס
    1.22
     النق
    1.13
     τε
    1.10
     alla
    1.05
    Activations Density 0.004%

    No Known Activations