© 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. 58092
    Prev
    Next
    INDEX
    Explanations

    sorowe, scowling, marowak

    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
    .
    1.58
     jeopard
    1.05
    IVE
    0.99
     as
    0.94
    가
    0.90
     incentiv
    0.88
    드시
    0.86
    에요
    0.83
     do
    0.82
    {
    0.82
    POSITIVE LOGITS
    ک
    1.37
    a
    1.30
    ال
    1.21
    ث
    1.16
    া
    1.15
    ne
    1.11
     powied
    1.11
     A
    1.09
    la
    1.06
    lt
    1.06
    Activations Density 0.002%

    No Known Activations