© 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. 218853
    Prev
    Next
    INDEX
    Explanations

    api request headers

    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
     സൗ
    0.41
    ōu
    0.40
    ्रू
    0.38
    Utc
    0.37
    achelorette
    0.37
    aisa
    0.37
    ^{*}=\
    0.37
    neo
    0.36
    cA
    0.36
    ᵁ
    0.36
    POSITIVE LOGITS
    yp
    0.47
     ja
    0.38
    者の
    0.38
    Forg
    0.38
    PILE
    0.38
    ibil
    0.37
     vi
    0.36
    Pile
    0.36
     Cel
    0.36
     cursing
    0.36
    Activations Density 0.000%

    No Known Activations