© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52082
    Prev
    Next
    INDEX
    Explanations

    scope and deliverables

    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_31_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
     pricing
    0.41
     stock
    0.40
     trusting
    0.38
    cherche
    0.38
    usstsein
    0.38
    믿
    0.38
     inspirado
    0.36
    atype
    0.36
     પ્રથમ
    0.36
    構築
    0.36
    POSITIVE LOGITS
    Counsel
    0.39
    Lowercase
    0.38
    েলে
    0.37
    Seminar
    0.36
     Semin
    0.35
     ভয়ানক
    0.35
    浇
    0.35
    Documents
    0.34
     Tables
    0.34
    Newly
    0.34
    Activations Density 0.001%

    No Known Activations