© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80364
    Prev
    Next
    INDEX
    Explanations

    greetings, specific greetings, slipper souk

    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_0_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
    과의
    1.38
    ტ
    1.34
     for
    1.24
     as
    1.21
    يد
    1.20
    ۹
    1.20
     by
    1.20
    lerinde
    1.16
    }
    1.16
     about
    1.13
    POSITIVE LOGITS
    on
    1.75
    ’
    1.55
    et
    1.50
    ों
    1.45
    s
    1.40
    א
    1.34
    ни
    1.34
    ار
    1.32
    he
    1.25
    ed
    1.21
    Activations Density 0.000%

    No Known Activations