© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 111758
    Prev
    Next
    INDEX
    Explanations

    "Kaiber" AI

    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_2_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
    2
    1.56
    ２
    1.36
    of
    1.34
    
    1.25
    在
    1.22
    ଶ
    1.22
    𝟮
    1.17
    ج
    1.16
    ся
    1.13
    to
    1.11
    POSITIVE LOGITS
    ro
    1.12
    י
    1.09
    ด
    1.05
    ل
    1.02
    ร
    1.02
    ut
    1.01
    ล
    0.94
    N
    0.92
    it
    0.89
    ي
    0.88
    Activations Density 0.001%

    No Known Activations