© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129926
    Prev
    Next
    INDEX
    Explanations

    F(n) fibonacci sequence

    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_6_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
     be
    1.30
    {
    1.10
    -
    1.04
     can
    0.97
    י
    0.91
    س
    0.90
    ,
    0.88
    ב
    0.84
    =
    0.83
    ส
    0.81
    POSITIVE LOGITS
     Те
    0.91
    ﺎ
    0.90
     Ва
    0.88
     типу
    0.85
    ﻤ
    0.82
     От
    0.82
    ти
    0.81
     vecchio
    0.80
    ariş
    0.80
     ιστο
    0.79
    Activations Density 0.007%

    No Known Activations