© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196569
    Prev
    Next
    INDEX
    Explanations

    helping people

    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_46_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
    mier
    0.47
    bricks
    0.43
     micro
    0.41
     న
    0.38
    Hammer
    0.37
    micro
    0.37
     craft
    0.36
     billi
    0.36
     nô
    0.35
     N
    0.35
    POSITIVE LOGITS
    Helping
    0.48
    幫助
    0.45
     অপরি
    0.44
    帮助
    0.43
    帮忙
    0.43
     допомогти
    0.42
     Helping
    0.42
    helping
    0.41
     helping
    0.41
     tech
    0.41
    Activations Density 0.003%

    No Known Activations