© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 204635
    Prev
    Next
    INDEX
    Explanations

    dropdown component

    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
     Ayn
    0.48
     AIA
    0.46
     Atlas
    0.42
     integrator
    0.41
     Regis
    0.40
    溉
    0.40
    ேட்
    0.39
     इंटीग्रेशन
    0.39
     엔진
    0.39
    okeh
    0.38
    POSITIVE LOGITS
    Change
    0.39
     bille
    0.37
    Test
    0.36
    semb
    0.36
     trom
    0.35
    骚
    0.35
    COOL
    0.34
     plaster
    0.34
    TEST
    0.33
     pessoa
    0.33
    Activations Density 0.003%

    No Known Activations