© 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. 164059
    Prev
    Next
    INDEX
    Explanations

    es kommt zu

    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
     retort
    0.56
    SMS
    0.54
     sensational
    0.50
    Popular
    0.49
     muscular
    0.48
     ladle
    0.48
    𝗝
    0.47
    Эта
    0.46
     cholester
    0.45
    Thrown
    0.45
    POSITIVE LOGITS
     đều
    0.67
    нови
    0.66
     giá
    0.63
    ц
    0.63
    и
    0.59
    пи
    0.58
    ني
    0.58
     heals
    0.58
     furono
    0.57
    ě
    0.57
    Activations Density 0.000%

    No Known Activations