© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170792
    Prev
    Next
    INDEX
    Explanations

    depth of field

    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_20_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
     vypl
    0.43
    מס
    0.40
     হ্
    0.39
    ❧
    0.39
     plunged
    0.38
    deutsche
    0.38
    ्रे
    0.38
    },}
    0.38
    midt
    0.38
    дони
    0.38
    POSITIVE LOGITS
    ija
    0.47
    olda
    0.46
     строй
    0.43
    AS
    0.43
     көрс
    0.43
    ego
    0.43
     hierarch
    0.42
     whitespace
    0.42
     ತೋರಿಸ
    0.41
    宀
    0.41
    Activations Density 0.001%

    No Known Activations