© 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. 171738
    Prev
    Next
    INDEX
    Explanations

    momentum

    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
    Offering
    0.44
    ﺓ
    0.44
     Offering
    0.44
     хода
    0.42
    ährung
    0.42
     Designation
    0.42
    ่าน
    0.41
    INATION
    0.40
    pples
    0.40
    さ
    0.39
    POSITIVE LOGITS
     obstruct
    0.50
     elektrol
    0.42
    ῃ
    0.42
    丼
    0.42
    abil
    0.41
     menstru
    0.40
    ন্দ্র
    0.40
    ic
    0.39
     obstructing
    0.39
    arp
    0.39
    Activations Density 0.001%

    No Known Activations