© 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. 108331
    Prev
    Next
    INDEX
    Explanations

    EBIT or EBITDA

    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
    ?
    1.27
     (
    1.09
    s
    1.06
    ки
    1.02
    !
    0.99
    lbl
    0.97
    lt
    0.96
    lords
    0.96
    <h2>
    0.94
    ryan
    0.93
    POSITIVE LOGITS
     can
    1.48
    ある
    1.39
     esempio
    1.38
    ک
    1.35
    ون
    1.32
     anál
    1.32
    ing
    1.29
    وی
    1.25
     acordo
    1.22
     hrane
    1.22
    Activations Density 0.000%

    No Known Activations