© 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
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 139498
    Prev
    Next
    INDEX
    Explanations

    reflective essay, paper, or practice

    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
     කරන
    0.55
    ivasena
    0.54
    ho
    0.52
    jel
    0.52
    ampshire
    0.50
    ساب
    0.49
     خوبی
    0.49
    )=
    0.49
    uar
    0.49
    selt
    0.48
    POSITIVE LOGITS
     Poly
    0.56
     Separ
    0.55
     stunned
    0.55
     fleeing
    0.52
     kidnapped
    0.52
     ML
    0.51
     From
    0.51
     Escape
    0.50
     recalling
    0.50
     Star
    0.50
    Activations Density 0.000%

    No Known Activations