© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203116
    Prev
    Next
    INDEX
    Explanations

    challenging negative beliefs

    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_12_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
    Edition
    0.46
    ointed
    0.46
     rpg
    0.46
    ulated
    0.45
    剥
    0.45
     व्यापारियों
    0.45
    ildenafil
    0.45
    acz
    0.44
    enhancing
    0.44
    ceded
    0.44
    POSITIVE LOGITS
    ][
    0.54
    selValue
    0.51
    ্যাপ
    0.50
     Sonos
    0.50
    AF
    0.49
     första
    0.47
     kojoj
    0.47
     substituir
    0.46
     Muhammed
    0.46
     THEY
    0.45
    Activations Density 0.000%

    No Known Activations