© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 178700
    Prev
    Next
    INDEX
    Explanations

    names

    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_50_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
    밀
    0.43
     কার্যত
    0.41
     दंड
    0.37
    दंड
    0.37
    楯
    0.37
     Rodgers
    0.36
     pruebas
    0.36
     Ribeiro
    0.35
    แมนเชสเตอร์ซิตี
    0.35
    엿
    0.34
    POSITIVE LOGITS
     scrapping
    0.42
    ﺫ
    0.39
    ventura
    0.39
    ží
    0.39
    GRESS
    0.38
    ঘট
    0.38
     gyro
    0.38
     jubil
    0.38
    belongs
    0.37
    ობის
    0.37
    Activations Density 0.001%

    No Known Activations