© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 174193
    Prev
    Next
    INDEX
    Explanations

    performed or conducted

    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
    fälle
    0.46
    datei
    0.45
     મોટી
    0.45
    azada
    0.44
    zeichnis
    0.44
    airlines
    0.44
    }$-
    0.43
    huis
    0.43
    airline
    0.43
    eniz
    0.42
    POSITIVE LOGITS
     ako
    0.48
     आणखी
    0.47
     coeur
    0.46
     Ako
    0.45
     यहाँ
    0.43
    𝗈
    0.43
     winds
    0.43
     bottling
    0.43
     строк
    0.42
     ако
    0.41
    Activations Density 0.000%

    No Known Activations