© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34674
    Prev
    Next
    INDEX
    Explanations

    telling stories and tales

    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_31_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
    uellement
    0.37
     Generalized
    0.37
    odyne
    0.36
    ়
    0.36
     वायू
    0.36
     amused
    0.35
    PLING
    0.35
    ULT
    0.35
     isang
    0.35
     kara
    0.34
    POSITIVE LOGITS
     преимущества
    0.37
    واره
    0.36
    ಗ
    0.36
    狒
    0.36
     Tune
    0.35
     നടപ
    0.35
    খি
    0.35
     Gather
    0.35
    চনার
    0.35
     tune
    0.34
    Activations Density 0.005%

    No Known Activations