© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 143176
    Prev
    Next
    INDEX
    Explanations

    GMT or CLR followed by delimiters

    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_0_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
     was
    1.47
    は
    1.40
    もの
    1.34
     can
    1.21
     كان
    1.20
     был
    1.17
     था
    1.16
    রামর্শ
    1.13
     которым
    1.12
     بال
    1.10
    POSITIVE LOGITS
    ת
    2.16
    т
    2.09
    ర్
    2.05
    ט
    2.05
    ل
    1.95
    د
    1.83
    ल
    1.80
    า
    1.77
    л
    1.72
    ર
    1.66
    Activations Density 0.000%

    No Known Activations