© 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. 112558
    Prev
    Next
    INDEX
    Explanations

    letras and letters

    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
    of
    1.44
    dengan
    1.13
    ۹
    1.11
    ۰
    1.10
    も
    1.05
    dalam
    0.95
    l
    0.91
    0.89
    dSample
    0.87
    も含
    0.85
    POSITIVE LOGITS
    م
    1.28
     it
    1.21
    و
    1.20
    на
    1.18
    ו
    1.16
    نا
    1.13
    وم
    1.09
    ون
    1.08
    ர
    1.08
    ant
    1.07
    Activations Density 0.000%

    No Known Activations