© 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. 175876
    Prev
    Next
    INDEX
    Explanations

    Linear Algebra

    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
     Lemb
    0.38
    ﮟ
    0.38
    νοι
    0.37
    સિંહ
    0.37
     பிரச்சினை
    0.37
     பணியா
    0.36
    蘸
    0.36
    𝗟
    0.36
     ವ
    0.35
    νή
    0.35
    POSITIVE LOGITS
    دون
    0.42
     terrible
    0.40
     Alger
    0.39
     wrong
    0.38
     horrible
    0.38
     Alz
    0.38
    ongo
    0.37
    xx
    0.37
    骋
    0.37
     கூறும்
    0.36
    Activations Density 0.001%

    No Known Activations