© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 234812
    Prev
    Next
    INDEX
    Explanations

    I

    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_46_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
     registr
    0.39
     findViewById
    0.39
     felt
    0.38
    (\|\
    0.38
    飘
    0.38
     advocate
    0.37
    FAPI
    0.36
     συνα
    0.36
    ption
    0.36
     voice
    0.36
    POSITIVE LOGITS
     выну
    0.45
    딧
    0.41
    क्रो
    0.39
     इजी
    0.39
     való
    0.39
    henium
    0.38
     Schiff
    0.38
     वास्तव
    0.37
    unction
    0.37
     ώ
    0.37
    Activations Density 0.002%

    No Known Activations