© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13117
    Prev
    Next
    INDEX
    Explanations

    drug abuse

    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_13_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
    '
    0.41
     variedad
    0.39
     fue
    0.36
     veces
    0.34
     كانت
    0.33
    ..
    0.33
              
    0.33
     رغم
    0.33
     perdere
    0.32
     como
    0.32
    POSITIVE LOGITS
    ｔ
    0.36
     pemberian
    0.35
    ബരി
    0.34
    Ⅹ
    0.34
     都
    0.34
     度
    0.34
    DER
    0.33
     പ്രവര്‍ത്തി
    0.33
    जत
    0.33
    uetooth
    0.33
    Activations Density 0.008%

    No Known Activations