© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199850
    Prev
    Next
    INDEX
    Explanations

    "Pinnacle" or "voice" context

    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_12_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
     !
    0.52
     petrol
    0.43
    !
    0.42
    int
    0.41
    ।”
    0.40
    Petrol
    0.39
    <strong>
    0.39
    <0xC2>
    0.39
     ”
    0.39
    Fort
    0.39
    POSITIVE LOGITS
    uvieron
    0.52
     Antrieb
    0.49
     ರೀತಿಯ
    0.49
     Ciências
    0.49
    curities
    0.48
     Zeng
    0.48
     ನಿಜ
    0.48
     Jaaye
    0.48
     Jego
    0.47
     riesce
    0.47
    Activations Density 0.000%

    No Known Activations