© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 168040
    Prev
    Next
    INDEX
    Explanations

    habit stacking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_34_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
     scrolled
    0.37
     संबोधित
    0.36
    hydrocèle
    0.36
    luents
    0.35
    坐
    0.35
     coin
    0.35
     direction
    0.34
    лку
    0.34
    解决方法
    0.34
    ScrollPane
    0.34
    POSITIVE LOGITS
    𝕀
    0.41
    anners
    0.40
    डू
    0.39
    banners
    0.37
    caling
    0.36
    Installing
    0.36
     고민
    0.36
    Branch
    0.36
    两年
    0.35
    ភ្ជាប់
    0.35
    Activations Density 0.005%

    No Known Activations