© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48827
    Prev
    Next
    INDEX
    Explanations

    initiatives and programs

    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_31_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
     дорогие
    0.36
    жными
    0.35
     standardised
    0.34
     Saran
    0.33
    綸
    0.33
     giveaways
    0.33
     guer
    0.32
    ]');
    0.32
     extensively
    0.31
     primates
    0.31
    POSITIVE LOGITS
    ocuk
    0.37
    ruce
    0.36
    orest
    0.36
     Haf
    0.36
    increase
    0.35
     அதிகரி
    0.35
     টেব
    0.35
     항공
    0.35
    ദു
    0.35
     gaman
    0.35
    Activations Density 0.004%

    No Known Activations