© 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-3-4B-IT
    3. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 9538
    Prev
    Next
    INDEX
    Explanations

    penetration

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    까지
    0.70
    rifft
    0.67
     hama
    0.66
    の時間
    0.65
     haver
    0.65
     沙
    0.65
    hoff
    0.64
    oir
    0.64
    ቦ
    0.64
     tume
    0.64
    POSITIVE LOGITS
     penet
    1.36
    Pen
    1.33
     Penet
    1.26
     penetration
    1.25
     pen
    1.20
     penetrated
    1.14
     penetrate
    1.14
     pén
    1.13
     Pen
    1.08
    penet
    1.08
    Activations Density 0.006%

    No Known Activations