© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198772
    Prev
    Next
    INDEX
    Explanations

    URLs and paths

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     wf
    0.43
    шень
    0.41
     SI
    0.40
     Simple
    0.39
     sunt
    0.38
     lh
    0.38
    蒂
    0.37
    ɢ
    0.37
     Settings
    0.37
     smut
    0.37
    POSITIVE LOGITS
    бах
    0.52
    válto
    0.41
     amph
    0.38
     छुट
    0.37
     pérd
    0.37
     formalized
    0.37
    beest
    0.36
    PL
    0.36
    offic
    0.36
    اديم
    0.35
    Activations Density 0.000%

    No Known Activations