© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 78553
    Prev
    Next
    INDEX
    Explanations

    task or instruction following

    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_53_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
     aps
    0.48
     v
    0.46
    apex
    0.43
    apses
    0.43
     Ves
    0.42
    xlink
    0.41
    spur
    0.39
     vesc
    0.39
     এপ
    0.39
    Apex
    0.38
    POSITIVE LOGITS
     grunds
    0.41
    ोब
    0.40
    uzo
    0.39
    າງ
    0.38
     vain
    0.38
    蚱
    0.38
    metto
    0.38
    aik
    0.38
     Dewar
    0.37
    naments
    0.37
    Activations Density 0.000%

    No Known Activations