© 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. 107897
    Prev
    Next
    INDEX
    Explanations

    number of

    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
    0
    1.82
     {
    1.36
     of
    1.19
    ב
    1.19
    ون
    1.10
    ה
    1.10
    지
    1.10
     by
    1.08
     Anonymous
    1.05
    ق
    1.05
    POSITIVE LOGITS
    that
    1.22
    ole
    1.16
     смесь
    1.08
    ada
    1.05
    et
    1.02
    raises
    1.02
     степень
    1.01
    ap
    1.00
    perme
    0.99
     طریق
    0.99
    Activations Density 0.001%

    No Known Activations