© 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. 60543
    Prev
    Next
    INDEX
    Explanations

    aroma / roma

    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
     It
    1.35
    ι
    1.26
    yl
    1.09
     There
    1.02
    It
    1.01
    an
    1.00
    ని
    1.00
    ни
    0.96
    ра
    0.93
     This
    0.92
    POSITIVE LOGITS
    𝗲
    1.27
    p
    1.26
    ד
    1.21
    𝗡
    1.21
    𝓭
    1.21
    ない
    1.20
    𝗢
    1.19
    b
    1.16
    𝗱
    1.14
    די
    1.10
    Activations Density 0.001%

    No Known Activations