© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61823
    Prev
    Next
    INDEX
    Explanations

    falta de

    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_2_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
    galkan
    0.93
    ንዳንድ
    0.85
     ветра
    0.85
    막
    0.84
    ivatives
    0.83
    괵
    0.82
     Highness
    0.81
     homologs
    0.81
     مبنی
    0.81
    goers
    0.80
    POSITIVE LOGITS
    1
    1.70
    ed
    1.59
    ي
    1.37
    4
    1.23
    e
    1.20
    5
    1.16
    i
    1.09
    يته
    1.09
     by
    1.05
    ១
    1.05
    Activations Density 0.005%

    No Known Activations