© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 2361
    Prev
    Next
    INDEX
    Explanations

    loved one, loss, 988

    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_40_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
    rought
    0.41
    kao
    0.37
    叼
    0.36
     tin
    0.36
    !!!!!!
    0.35
    atever
    0.35
    撩
    0.35
    каз
    0.34
    কাব
    0.34
     healthy
    0.34
    POSITIVE LOGITS
     Pneum
    0.47
     Essence
    0.41
     espí
    0.41
    লোড
    0.40
     conditioned
    0.39
     Meade
    0.39
     Cond
    0.39
     Conditioning
    0.37
     دوستان
    0.37
    
    0.37
    Activations Density 0.072%

    No Known Activations