© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 3280
    Prev
    Next
    INDEX
    Explanations

    say "cup"

    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_44_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
    <0x91>
    0.48
    𝟮
    0.41
     ۲۰۰
    0.39
    jst
    0.38
    ophila
    0.38
    enen
    0.38
    ۲
    0.38
    isseur
    0.38
     нес
    0.38
    riet
    0.37
    POSITIVE LOGITS
     Six
    0.64
     six
    0.59
     Five
    0.58
     Seven
    0.58
    six
    0.55
     five
    0.55
     seven
    0.55
     七
    0.53
     bảy
    0.53
    Five
    0.52
    Activations Density 0.081%

    No Known Activations