© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13562
    Prev
    Next
    INDEX
    Explanations

    Dart syntax and keywords

    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_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
    ರ್ಧ
    0.44
    RefManager
    0.44
    屈
    0.41
    ेश्च
    0.40
    +|\
    0.38
     canon
    0.38
    ethylsulfanyl
    0.37
    pton
    0.37
    エス
    0.37
    पीसी
    0.36
    POSITIVE LOGITS
     pump
    0.42
     pumps
    0.40
     trump
    0.40
    —
    0.39
     joint
    0.38
     sends
    0.38
     flying
    0.38
     most
    0.38
     pud
    0.37
     spins
    0.37
    Activations Density 0.004%

    No Known Activations