© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42822
    Prev
    Next
    INDEX
    Explanations

    pinpoint location or source

    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_13_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
     வட
    0.40
    र्च
    0.40
     வளர்
    0.37
     Diabetic
    0.37
    illation
    0.36
    栃
    0.36
    t
    0.36
    to
    0.36
    ines
    0.35
    UTORY
    0.35
    POSITIVE LOGITS
    จาก
    0.46
     tanggal
    0.43
     mysterious
    0.41
    REGIUNE
    0.40
     congressional
    0.38
     Mysterious
    0.38
     dari
    0.37
     birçok
    0.37
     ottimo
    0.37
     menyebabkan
    0.37
    Activations Density 0.052%

    No Known Activations