© 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. 36274
    Prev
    Next
    INDEX
    Explanations

    something vaguely / faintly / metallic

    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
    d
    1.08
    b
    0.88
    m
    0.80
    s
    0.76
     Trichodesmium
    0.70
    dnn
    0.70
     directs
    0.68
    strokeStyle
    0.67
     volumetric
    0.66
     concaten
    0.64
    POSITIVE LOGITS
    า
    1.07
     as
    1.05
    다
    1.02
    ة
    0.95
    ون
    0.89
    ية
    0.89
     be
    0.88
    وم
    0.85
    на
    0.84
    ки
    0.84
    Activations Density 0.030%

    No Known Activations