© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21459
    Prev
    Next
    INDEX
    Explanations

    Ger

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     verificare
    0.43
    iple
    0.40
    ตรวจสอบ
    0.39
    iving
    0.38
    恢
    0.37
    jos
    0.37
    veren
    0.37
    টিভ
    0.36
    VER
    0.36
    resses
    0.36
    POSITIVE LOGITS
    orten
    0.39
    ightly
    0.38
    ots
    0.36
    டா
    0.36
     Cuenta
    0.36
    𝜇
    0.36
    orts
    0.36
     updateTotal
    0.34
    显得
    0.34
    لام
    0.34
    Activations Density 0.005%

    No Known Activations