© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 214135
    Prev
    Next
    INDEX
    Explanations

    technical or 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_43_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
    <0xB2>
    0.45
     Keystone
    0.41
     marca
    0.40
     six
    0.39
    6
    0.39
     Dina
    0.38
    ۶
    0.38
    innings
    0.37
     zuz
    0.37
     шести
    0.37
    POSITIVE LOGITS
    一体
    0.41
    琉
    0.39
    0.38
    гии
    0.37
     Ann
    0.37
    indexPath
    0.36
    廂
    0.35
     సమ
    0.35
     Harus
    0.34
    ósticos
    0.34
    Activations Density 0.009%

    No Known Activations