© 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. 88339
    Prev
    Next
    INDEX
    Explanations

    entering, brand, fund, iron

    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
    1
    0.75
    0
    0.75
    \
    0.73
    ts
    0.72
    ’
    0.71
    si
    0.67
    ی
    0.64
    ’,
    0.63
    ’?
    0.63
    ों
    0.62
    POSITIVE LOGITS
    ת
    0.86
    に
    0.72
    च्या
    0.69
     NDA
    0.63
    थुरा
    0.62
    S
    0.62
    ना
    0.60
    ędzy
    0.60
     blazing
    0.60
    ер
    0.59
    Activations Density 0.001%

    No Known Activations