© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53163
    Prev
    Next
    INDEX
    Explanations

    total and quantity specifications

    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_30_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
     magnolia
    0.39
    liğini
    0.38
    ]$-
    0.36
    に合わせて
    0.36
    后
    0.35
    နှင့်
    0.34
    ramethyl
    0.34
    uitively
    0.34
     Функция
    0.33
    のは
    0.33
    POSITIVE LOGITS
    𝐝
    0.40
     periodicity
    0.39
     subdivision
    0.37
     subdiv
    0.36
    Trad
    0.36
     первое
    0.35
    👆
    0.35
     descript
    0.34
     طرز
    0.34
     Subdivision
    0.34
    Activations Density 0.000%

    No Known Activations