© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242911
    Prev
    Next
    INDEX
    Explanations

    outputting or coming out

    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_40_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
    េះ
    0.38
     బీ
    0.38
     disrupt
    0.37
     Bad
    0.37
    étr
    0.37
     disruptive
    0.37
    वॉ
    0.36
    (&:
    0.36
     jug
    0.36
    zicht
    0.36
    POSITIVE LOGITS
    出て
    0.50
    出る
    0.49
     вышел
    0.46
    に出て
    0.46
    が出る
    0.45
     kelu
    0.45
     çıktı
    0.45
     salió
    0.44
     outfile
    0.44
     OUTPUT
    0.43
    Activations Density 0.007%

    No Known Activations