© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122271
    Prev
    Next
    INDEX
    Explanations

    location or position

    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_3_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
    د
    0.98
     on
    0.74
    지만
    0.73
     debates
    0.67
    ח
    0.64
    ৫
    0.64
     nación
    0.64
    یم
    0.63
    보니
    0.63
     przyję
    0.63
    POSITIVE LOGITS
    1
    1.08
    0
    0.88
    3
    0.72
    jong
    0.68
    ↵
    0.67
    }$
    0.67
    ase
    0.64
    over
    0.62
    etch
    0.62
    Inn
    0.62
    Activations Density 0.008%

    No Known Activations