© 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. 40136
    Prev
    Next
    INDEX
    Explanations

    Ending with 'e'

    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
     NES
    0.50
     бет
    0.45
     SES
    0.45
    нета
    0.45
    erei
    0.44
    SES
    0.43
     bey
    0.43
    헴
    0.42
     нес
    0.42
    Ses
    0.41
    POSITIVE LOGITS
    fe
    0.87
    pe
    0.86
     le
    0.83
    Ke
    0.83
     LE
    0.82
     Ke
    0.80
    le
    0.78
    be
    0.78
    ke
    0.78
    he
    0.78
    Activations Density 0.135%

    No Known Activations