© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1222
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
     nine
    0.47
    ៩
    0.46
     ९
    0.44
    
    0.43
     neun
    0.42
     Scaling
    0.42
    Scaling
    0.41
    ৯
    0.41
     raising
    0.39
     поднима
    0.39
    POSITIVE LOGITS
    oteric
    0.40
    clide
    0.38
    દર્શન
    0.38
    muj
    0.38
    ced
    0.37
    days
    0.37
    ioned
    0.37
    월
    0.37
    datum
    0.36
    drag
    0.36
    Activations Density 0.029%

    No Known Activations