© 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. 56752
    Prev
    Next
    INDEX
    Explanations

    type definition or property

    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
    <0x94>
    0.52
    altungen
    0.49
    agen
    0.48
    itt
    0.48
    örungen
    0.47
    ate
    0.46
    netflix
    0.45
    ami
    0.45
     त्यावेळी
    0.45
     flamenco
    0.44
    POSITIVE LOGITS
     divides
    0.61
    (
    0.59
     impug
    0.55
    ヤー
    0.55
     에
    0.54
     divisible
    0.53
     spits
    0.53
    벧
    0.53
     goods
    0.52
    <unused85>
    0.52
    Activations Density 0.005%

    No Known Activations