© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2816
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    𝒹
    0.42
     انتہائی
    0.41
     боюнча
    0.41
    醮
    0.40
    ᒥ
    0.39
    肐
    0.39
    𝘥
    0.39
     amazingly
    0.38
    𒊕
    0.38
     سبک
    0.37
    POSITIVE LOGITS
     Commonwealth
    0.44
     constant
    0.43
     Ac
    0.41
    Constant
    0.41
     Constant
    0.40
     Guard
    0.39
     Fund
    0.39
     France
    0.38
     Or
    0.38
     port
    0.37
    Activations Density 0.000%

    No Known Activations