© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152147
    Prev
    Next
    INDEX
    Explanations

    phone number

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    both
    0.50
     entrambi
    0.43
    или
    0.42
     Mail
    0.41
    which
    0.40
    ,*
    0.40
     दोनों
    0.40
     Emails
    0.40
     или
    0.40
     ಅಥವಾ
    0.39
    POSITIVE LOGITS
     telephone
    0.50
    telephone
    0.46
    Telephone
    0.45
    PHONE
    0.44
     PHONE
    0.42
    <(
    0.40
    phone
    0.39
     mett
    0.39
    This
    0.38
     unlikely
    0.38
    Activations Density 0.001%

    No Known Activations