© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 103525
    Prev
    Next
    INDEX
    Explanations

    began building

    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_1_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
    ad
    1.51
    c
    1.42
    y
    1.41
    od
    1.30
    v
    1.30
    i
    1.23
    b
    1.23
    z
    1.22
    ang
    1.20
    em
    1.16
    POSITIVE LOGITS
    いた
    1.35
    あります
    1.20
    る
    1.18
    ක්
    1.16
    த்து
    1.15
    変
    1.15
    ある
    1.13
    ственных
    1.12
    ని
    1.09
    し
    1.09
    Activations Density 0.000%

    No Known Activations