© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158116
    Prev
    Next
    INDEX
    Explanations

    om chuối đậu

    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
    aría
    1.22
    ás
    1.12
    0
    1.09
    ations
    1.03
    ға
    0.96
     as
    0.94
    ímenes
    0.92
    ି
    0.92
    usions
    0.91
     이에
    0.89
    POSITIVE LOGITS
    י
    1.55
    ע
    1.54
    i
    1.51
    R
    1.46
    t
    1.40
    ت
    1.38
    o
    1.37
    c
    1.36
    り
    1.34
    G
    1.33
    Activations Density 0.000%

    No Known Activations