© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 134807
    Prev
    Next
    INDEX
    Explanations

    results of

    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_37_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
     Synchron
    0.41
    锉
    0.40
    十三
    0.37
    𝑭
    0.37
    <start_of_turn>
    0.36
    Synchron
    0.36
     synchronous
    0.36
     굉장
    0.35
    뺄
    0.35
     pouls
    0.35
    POSITIVE LOGITS
    continuous
    0.41
     بوا
    0.40
    墠
    0.40
    carts
    0.40
     continuous
    0.38
    mite
    0.38
     continuously
    0.38
     accreditation
    0.37
     sult
    0.36
     BU
    0.36
    Activations Density 0.000%

    No Known Activations