© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195364
    Prev
    Next
    INDEX
    Explanations

    `huggingface-cli`, `webpack-cli`

    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_15_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
     Brust
    0.51
     menek
    0.48
     Lef
    0.48
     ফেব্রুয়ার
    0.47
    븐
    0.46
     Fluss
    0.46
     Sheppard
    0.46
     c
    0.45
     copp
    0.45
     computerChoice
    0.45
    POSITIVE LOGITS
     Figura
    0.59
    Ի
    0.58
     الدهون
    0.56
    ixi
    0.55
    ర్స్
    0.53
    的所有
    0.51
    ż
    0.51
    rs
    0.51
    ئی
    0.51
    ٨
    0.51
    Activations Density 0.001%

    No Known Activations