© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41907
    Prev
    Next
    INDEX
    Explanations

    promoting sustainability

    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_22_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
    珵
    0.18
     Theorie
    0.16
     TERMIN
    0.15
     פון
    0.15
     outnumbered
    0.15
     FOUR
    0.15
    广州
    0.15
     тү
    0.15
    ந்துள்ளது
    0.15
    풍
    0.15
    POSITIVE LOGITS
    PreferenceKey
    0.18
     export
    0.17
     อ่ะ
    0.16
    acks
    0.16
     restrain
    0.16
     standardize
    0.15
     shortly
    0.15
     passports
    0.15
     betterment
    0.15
     restraints
    0.15
    Activations Density 0.007%

    No Known Activations