© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25680
    Prev
    Next
    INDEX
    Explanations

    manager reporting or feedback

    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_10_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
    ف
    0.20
    ி
    0.18
     întreb
    0.17
     hz
    0.17
    ্ম
    0.17
    aton
    0.17
    utives
    0.17
    ि
    0.17
    adinam
    0.17
    ъем
    0.17
    POSITIVE LOGITS
     B
    0.21
     T
    0.20
    t
    0.19
     D
    0.19
    }$.
    0.19
    }=\
    0.18
    ，
    0.18
     W
    0.18
     P
    0.18
    ，“
    0.17
    Activations Density 0.010%

    No Known Activations