© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13899
    Prev
    Next
    INDEX
    Explanations

    quantization or clockwise rotation

    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_13_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
    C
    0.54
    0.49
    www
    0.49
    aduras
    0.46
     C
    0.44
    DR
    0.43
    forms
    0.41
     www
    0.41
     d
    0.40
    Dr
    0.39
    POSITIVE LOGITS
    renzia
    0.46
    ीकरण
    0.45
    вени
    0.45
    пенди
    0.45
    дото
    0.43
     മിക
    0.43
    ($('#
    0.42
     Estudio
    0.42
    市立
    0.42
    嗇
    0.42
    Activations Density 0.014%

    No Known Activations