© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 214002
    Prev
    Next
    INDEX
    Explanations

    Lis

    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_47_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
     T
    0.47
    T
    0.43
     Bonif
    0.43
     Tis
    0.41
     Flanagan
    0.41
     Jameson
    0.40
     Presley
    0.40
    쿤
    0.39
     चेतावनी
    0.39
    Mind
    0.38
    POSITIVE LOGITS
    াটো
    0.38
    ierungen
    0.38
    nikom
    0.36
     subarrays
    0.35
    ниците
    0.35
    скае
    0.35
     devra
    0.34
    ្អ
    0.34
     MONT
    0.34
     subcontractor
    0.34
    Activations Density 0.000%

    No Known Activations