© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 179713
    Prev
    Next
    INDEX
    Explanations

    function calls or definitions

    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_29_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
     echar
    0.42
     bifur
    0.36
     поді
    0.36
     ingress
    0.36
     insulation
    0.36
    音
    0.36
    trasound
    0.35
    止め
    0.35
    ASSI
    0.35
    多种
    0.35
    POSITIVE LOGITS
     Coney
    0.40
    耒
    0.40
     Seth
    0.39
     Prep
    0.39
     Riverside
    0.38
    ૄ
    0.38
     Mild
    0.38
     Khu
    0.37
    اندان
    0.37
     AppMethodBeat
    0.36
    Activations Density 0.003%

    No Known Activations