© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 103198
    Prev
    Next
    INDEX
    Explanations

    about

    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_44_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
     येते
    0.38
     behold
    0.38
     Прав
    0.38
    Dangerous
    0.37
    来实现
    0.36
     commission
    0.36
     Pared
    0.36
    𝒔
    0.35
    拿到
    0.35
    tom
    0.34
    POSITIVE LOGITS
    Cp
    0.41
     worldly
    0.41
    localVar
    0.40
     To
    0.39
     Cp
    0.38
    licka
    0.37
    lynk
    0.37
     আবুল
    0.36
     любить
    0.36
    links
    0.36
    Activations Density 0.008%

    No Known Activations