© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 160633
    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_2_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
    し
    1.37
    مه
    1.16
    يل
    1.15
    ED
    1.04
    nal
    1.03
    ren
    1.01
    ished
    1.00
    ligt
    1.00
     estratég
    1.00
    ni
    0.99
    POSITIVE LOGITS
    ת
    1.85
    ר
    1.67
    ۰
    1.56
    at
    1.49
    is
    1.38
    0
    1.34
    ०
    1.33
    ០
    1.30
    ה
    1.28
    ol
    1.27
    Activations Density 0.000%

    No Known Activations