© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 209823
    Prev
    Next
    INDEX
    Explanations

    hydroxyl and atmosphere

    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_10_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
     atmosphere
    0.30
    气氛
    0.27
    ک
    0.26
    雰囲気
    0.25
    ियल
    0.23
    charge
    0.23
    adic
    0.23
     atmospheres
    0.23
    წიფ
    0.23
    イッチ
    0.22
    POSITIVE LOGITS
     eigenen
    0.30
    ↵
    0.28
    lö
    0.26
    َ
    0.25
    Ế
    0.25
    ние
    0.25
     hebben
    0.24
     persönlichen
    0.24
     män
    0.24
     Welt
    0.24
    Activations Density 0.004%

    No Known Activations