© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 58888
    Prev
    Next
    INDEX
    Explanations

    spit it out

    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
    i
    2.41
    in
    2.19
    P
    1.81
    C
    1.71
    M
    1.71
    D
    1.70
    l
    1.67
    B
    1.66
     for
    1.59
    X
    1.55
    POSITIVE LOGITS
    리
    1.25
    يس
    1.23
    я
    1.23
    ీ
    1.22
    ί
    1.20
    ен
    1.20
     on
    1.15
    ни
    1.15
    اري
    1.13
    ásticos
    1.10
    Activations Density 0.000%

    No Known Activations