© 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. 86783
    Prev
    Next
    INDEX
    Explanations

    misconceptions, concepts, conscripts

    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
    い
    0.69
    बाट
    0.64
     perceptive
    0.63
    し
    0.63
    ου
    0.59
     classy
    0.59
    ப்படுகிறது
    0.58
     phospholipid
    0.58
     pemb
    0.56
    к
    0.56
    POSITIVE LOGITS
    concept
    0.86
    3
    0.79
    2
    0.76
    7
    0.75
    -
    0.75
    4
    0.71
    Concept
    0.68
    concepts
    0.68
    ur
    0.65
    ne
    0.65
    Activations Density 0.000%

    No Known Activations