© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167277
    Prev
    Next
    INDEX
    Explanations

    Old Man

    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_34_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
    SelectSingleNode
    0.35
     personne
    0.34
    माग
    0.34
     potions
    0.34
     prese
    0.34
    婼
    0.34
    িমের
    0.33
    洊
    0.33
     personen
    0.32
     osoba
    0.32
    POSITIVE LOGITS
    ذور
    0.40
     Indira
    0.40
     explain
    0.39
    ektiv
    0.38
     ইন্দিরা
    0.37
    クリスマス
    0.37
    ategor
    0.36
     Explain
    0.36
    jdk
    0.36
    feitura
    0.36
    Activations Density 0.002%

    No Known Activations