© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36944
    Prev
    Next
    INDEX
    Explanations

    perception of Riskperception of businessperception of "Cuteness"perception of Intentperception of noiseperception of catsperception of activistperception of sound

    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_3_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
    2
    0.90
    ல்
    0.75
    ര്‍
    0.71
    ى
    0.70
     soir
    0.63
     sprach
    0.63
    }</
    0.62
     gente
    0.61
    تيجة
    0.59
    يل
    0.59
    POSITIVE LOGITS
     is
    0.88
    t
    0.76
    is
    0.72
    را
    0.67
     apportionment
    0.67
    O
    0.67
     crystallization
    0.65
    Ⲥ
    0.65
    ول
    0.64
     permeability
    0.64
    Activations Density 0.001%

    No Known Activations