© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199417
    Prev
    Next
    INDEX
    Explanations

    library suffixes

    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_27_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
    ㄼ
    0.41
     psicología
    0.39
    礽
    0.38
     depository
    0.36
    লগ্ন
    0.35
    炝
    0.35
     phosphat
    0.35
    摡
    0.34
     одним
    0.34
     repositorio
    0.34
    POSITIVE LOGITS
    cius
    0.39
    this
    0.37
    fancy
    0.37
    inating
    0.37
    creative
    0.36
    ìn
    0.36
    twe
    0.36
    வ்வா
    0.35
    ostridium
    0.35
    在这个
    0.34
    Activations Density 0.000%

    No Known Activations