© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240942
    Prev
    Next
    INDEX
    Explanations

    new object initialization

    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_25_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
    :
    0.47
     :
    0.46
     Became
    0.42
     .
    0.41
    .
    0.41
     Fris
    0.40
    .`
    0.39
     packs
    0.39
     fire
    0.39
     :,
    0.39
    POSITIVE LOGITS
     regrettable
    0.44
    劭
    0.41
     взгля
    0.39
     Рей
    0.39
    欣
    0.39
    فكير
    0.38
    મિક
    0.37
    vény
    0.37
    スプレイ
    0.37
    玮
    0.37
    Activations Density 0.000%

    No Known Activations