© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 161688
    Prev
    Next
    INDEX
    Explanations

    all-purpose flour

    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_31_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
    砓
    0.32
     목표
    0.28
    পশ্চ
    0.27
    紾
    0.26
     undercut
    0.25
     ಬಹಳ
    0.25
    ftl
    0.25
    /**
    0.24
     Salary
    0.24
    $_{
    0.24
    POSITIVE LOGITS
    ట్టి
    0.28
    ّة
    0.27
     Elements
    0.26
    σετε
    0.26
    档案馆
    0.25
    Elements
    0.25
     Pp
    0.25
    ूर
    0.25
    actment
    0.24
    cenie
    0.24
    Activations Density 0.002%

    No Known Activations