© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78927
    Prev
    Next
    INDEX
    Explanations

    direct or indirect answers

    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
    แค่
    0.39
     vibrant
    0.35
     viktigt
    0.35
     suff
    0.35
    \"");
    0.35
    lever
    0.34
    NEC
    0.34
    だけの
    0.34
     лишь
    0.34
    ﴿
    0.34
    POSITIVE LOGITS
     doss
    0.47
     直接
    0.44
     indire
    0.42
    Indirect
    0.42
    ன்
    0.40
     langsung
    0.38
     직접
    0.37
    ভূত
    0.37
     direto
    0.37
     አስተ
    0.37
    Activations Density 0.000%

    No Known Activations