© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1957
    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_40_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
     пуль
    0.38
     คลิ
    0.38
    నె
    0.36
    咊
    0.36
    ΗΣ
    0.35
     escrit
    0.35
    HasStarred
    0.35
    வராய்
    0.35
    ἴ
    0.34
    (""))
    0.34
    POSITIVE LOGITS
     Wait
    0.41
    commodity
    0.38
     অপে
    0.38
     Yes
    0.37
    wait
    0.37
     choke
    0.37
     wait
    0.37
     Const
    0.36
     Dai
    0.36
    yap
    0.35
    Activations Density 0.016%

    No Known Activations