© 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. 242902
    Prev
    Next
    INDEX
    Explanations

    ProStreet, HPV, magic, menacing

    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
     Participate
    0.40
    Independent
    0.38
     participates
    0.37
     participate
    0.37
    innitus
    0.37
    ঘা
    0.37
     Particip
    0.36
    頫
    0.35
     unsupervised
    0.35
    හාර
    0.35
    POSITIVE LOGITS
    ွား
    0.42
    )--
    0.42
    "--
    0.40
     values
    0.40
    }-{
    0.39
    値
    0.39
    ambil
    0.39
     Values
    0.39
     valori
    0.38
    auff
    0.38
    Activations Density 0.000%

    No Known Activations