© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3687
    Prev
    Next
    INDEX
    Explanations

    18th century style, proper nouns

    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_39_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
     বলছে
    0.42
     Victorian
    0.40
    ">)</
    0.38
     TEXAS
    0.36
    দেবের
    0.36
     gorgeous
    0.36
     cas
    0.35
     Chart
    0.35
    uria
    0.35
    kiwa
    0.35
    POSITIVE LOGITS
     conno
    0.41
    Jonathan
    0.38
    皇
    0.38
    Чу
    0.38
    Mr
    0.37
    compassing
    0.37
    ात्
    0.37
     Monsieur
    0.37
    Compass
    0.37
     whimsical
    0.37
    Activations Density 0.010%

    No Known Activations