© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36761
    Prev
    Next
    INDEX
    Explanations

    flashcard utility

    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_11_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
     breaths
    0.67
     była
    0.64
     breathes
    0.63
     breathe
    0.62
     collaborate
    0.60
    㧍
    0.60
     emphasise
    0.59
    нат
    0.57
    ue
    0.56
    ną
    0.55
    POSITIVE LOGITS
    "
    0.58
    ↵
    0.56
    civil
    0.55
    micro
    0.54
    trans
    0.54
    motor
    0.54
    自在
    0.53
    ځ
    0.52
    <h3>
    0.50
    MAX
    0.50
    Activations Density 0.000%

    No Known Activations