© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195480
    Prev
    Next
    INDEX
    Explanations

    squares, stretches, pairs, mixed

    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_4_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
    મ
    0.82
    ิน
    0.81
     идёт
    0.79
     .)
    0.77
    ő
    0.77
    ંમે
    0.76
    ين
    0.75
    ţi
    0.75
    йдёт
    0.75
    行う
    0.75
    POSITIVE LOGITS
    s
    1.88
    '
    1.35
    k
    1.34
    f
    1.30
    t
    1.24
    y
    1.24
    v
    1.24
    z
    1.21
    d
    1.20
    p
    1.14
    Activations Density 0.004%

    No Known Activations