© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248476
    Prev
    Next
    INDEX
    Explanations

    steamy

    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_56_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
     गरेको
    0.39
    StudioProjects
    0.37
    あえず
    0.36
    levation
    0.36
     Huan
    0.36
    กระ
    0.36
    ṟ
    0.36
    ហេ
    0.35
    вара
    0.35
    Pun
    0.34
    POSITIVE LOGITS
     ste
    0.92
     Ste
    0.88
    Ste
    0.73
     steer
    0.70
     сте
    0.67
    ste
    0.66
     STE
    0.66
     steers
    0.57
     Steff
    0.55
     steering
    0.53
    Activations Density 0.000%

    No Known Activations