© 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. 157101
    Prev
    Next
    INDEX
    Explanations

    envisioned

    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
    en
    1.21
    asma
    1.08
    erin
    1.07
    '
    1.03
    er
    1.02
    agnetic
    1.01
    edTest
    0.99
    al
    0.98
    asi
    0.98
    enso
    0.96
    POSITIVE LOGITS
    ק
    2.47
    פ
    1.65
    ס
    1.64
    ח
    1.55
     in
    1.53
    ร
    1.42
    ז
    1.34
     for
    1.28
    ุ
    1.27
    મ
    1.24
    Activations Density 0.000%

    No Known Activations