© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153864
    Prev
    Next
    INDEX
    Explanations

    currently using now

    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_23_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
     Ukraj
    0.47
    itors
    0.40
     conspicuous
    0.38
    orsz
    0.38
    <%=
    0.38
    कर्म
    0.37
     Rwand
    0.37
    匤
    0.36
    Penumpang
    0.36
    画像
    0.36
    POSITIVE LOGITS
    ρώ
    0.40
    ನೀ
    0.39
     اقبال
    0.39
    γεν
    0.38
    騙
    0.37
     удоб
    0.37
     Adopt
    0.36
     Behavior
    0.36
     મે
    0.35
    𝙨
    0.35
    Activations Density 0.016%

    No Known Activations