© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159085
    Prev
    Next
    INDEX
    Explanations

    gals or gale

    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_2_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
    ר
    1.66
    ל
    1.65
    на
    1.63
    ש
    1.53
    ه
    1.51
    י
    1.48
    at
    1.47
    ل
    1.39
    라
    1.31
    ح
    1.27
    POSITIVE LOGITS
    deki
    1.32
    col
    1.17
    。
    1.17
    ků
    1.16
    го
    1.15
    chen
    1.13
    даги
    1.10
    ca
    1.09
    cos
    1.09
    k
    1.09
    Activations Density 0.000%

    No Known Activations