© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249969
    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_56_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
     Westbrook
    0.42
     EXO
    0.40
    }^{-}$
    0.38
    <0xA6>
    0.38
    冒
    0.37
     ridden
    0.37
    しゃれ
    0.37
    }^{*}$.
    0.37
     দেওয়া
    0.36
    ,}$
    0.36
    POSITIVE LOGITS
     Score
    0.39
     Thing
    0.38
    ័
    0.38
    Uri
    0.38
     Speech
    0.38
     égale
    0.37
     égales
    0.37
    éfono
    0.37
    愷
    0.37
     igual
    0.37
    Activations Density 0.000%

    No Known Activations