© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123679
    Prev
    Next
    INDEX
    Explanations

    murky waters

    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_3_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
    ла
    1.09
    an
    1.02
    /
    0.96
    리
    0.94
    x
    0.93
    *
    0.90
    л
    0.82
    ки
    0.82
     (
    0.80
    -
    0.76
    POSITIVE LOGITS
     a
    0.91
     sonore
    0.79
     ಪ್ರಮಾಣ
    0.72
     appartient
    0.71
     informativo
    0.70
     keluar
    0.67
     reeks
    0.64
     man
    0.61
     ομά
    0.61
    ａ
    0.61
    Activations Density 0.000%

    No Known Activations