© 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. 157369
    Prev
    Next
    INDEX
    Explanations

    breathe out, life, deeply

    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
    ren
    1.17
    ุ
    1.07
     joka
    1.03
    vä
    1.02
    se
    1.01
    ées
    1.01
    men
    1.00
    বে
    0.99
    \
    0.99
     पर
    0.98
    POSITIVE LOGITS
    ли
    1.59
    ר
    1.40
    ۔
    1.31
     L
    1.20
    т
    1.20
     distraught
    1.17
    ת
    1.16
    is
    1.16
     K
    1.13
    י
    1.11
    Activations Density 0.005%

    No Known Activations