© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139098
    Prev
    Next
    INDEX
    Explanations

    standMethod used: Method 1Reason: All MAX_ACTIVATING_TOKENS are the same

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     standings
    0.50
     Rupees
    0.41
     proudly
    0.40
    getMessage
    0.40
     apart
    0.40
    苔
    0.40
    梵
    0.40
     stood
    0.39
    Apart
    0.39
    standen
    0.38
    POSITIVE LOGITS
    шчы
    0.38
    ylist
    0.36
     একেবারেই
    0.35
    ère
    0.34
    igheid
    0.34
    矸
    0.34
     اخ
    0.34
    svc
    0.34
     мало
    0.34
     mało
    0.33
    Activations Density 0.001%

    No Known Activations