© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 82415
    Prev
    Next
    INDEX
    Explanations

    roman numeral viii or english/chinese ordinal fourth

    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_0_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
    d
    2.17
    g
    2.16
    t
    2.11
    f
    2.09
    p
    2.03
    z
    2.02
    k
    1.93
    b
    1.91
    y
    1.89
    j
    1.79
    POSITIVE LOGITS
    ки
    1.69
    的
    1.55
    ные
    1.44
    ло
    1.42
    нения
    1.41
    사
    1.40
     laterales
    1.38
    ли
    1.30
    я
    1.30
    يل
    1.28
    Activations Density 0.000%

    No Known Activations