© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 150612
    Prev
    Next
    INDEX
    Explanations

    year

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    population
    0.43
    ausch
    0.41
    ሒ
    0.40
    simply
    0.39
    so
    0.38
    process
    0.38
    schedule
    0.38
    स्तिष्क
    0.38
    procedure
    0.37
    γι
    0.36
    POSITIVE LOGITS
     Between
    0.47
     /
    0.45
    **.
    0.44
     á
    0.43
    /_
    0.43
    /
    0.43
     /.
    0.40
     Upon
    0.40
     –
    0.40
    யம்
    0.40
    Activations Density 0.000%

    No Known Activations