© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164709
    Prev
    Next
    INDEX
    Explanations

    there he was

    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_31_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
    ไปด้วย
    0.38
     Dose
    0.38
    κης
    0.37
    ubercul
    0.36
    వ్వు
    0.36
     Come
    0.35
     apparaître
    0.35
    窦
    0.35
    咻
    0.35
    गें
    0.34
    POSITIVE LOGITS
     অসুবিধা
    0.40
    ModelGrid
    0.38
     감사
    0.38
     및
    0.37
    ability
    0.37
     poskyt
    0.37
     успі
    0.36
    으로서
    0.36
    ABILITY
    0.35
     стаби
    0.35
    Activations Density 0.001%

    No Known Activations