© 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. 204396
    Prev
    Next
    INDEX
    Explanations

    if you

    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
     ग्रस्त
    0.44
     any
    0.43
    $&$
    0.40
     Any
    0.38
    Any
    0.38
    δήποτε
    0.38
     ಇದು
    0.38
    |+
    0.38
     qualsiasi
    0.38
    唯一
    0.38
    POSITIVE LOGITS
    вости
    0.43
     聞い
    0.43
     missionaries
    0.39
    రుగులు
    0.37
     tutors
    0.37
    जों
    0.37
    ולנד
    0.36
     იყ
    0.36
    ENING
    0.36
     blanches
    0.35
    Activations Density 0.007%

    No Known Activations