© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 49907
    Prev
    Next
    INDEX
    Explanations

    performance and quality

    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_55_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
    imagen
    0.41
    Sens
    0.39
    ܚ
    0.38
    sens
    0.38
     reshape
    0.38
    rivi
    0.38
    眹
    0.37
    𝐒
    0.37
    Location
    0.37
    Gaming
    0.37
    POSITIVE LOGITS
     resolved
    0.39
     randomized
    0.37
     quarter
    0.36
     Boiler
    0.35
     দিল্লিতে
    0.35
     compromised
    0.34
     resolution
    0.34
     resolución
    0.34
     تیار
    0.34
     bureaus
    0.34
    Activations Density 0.001%

    No Known Activations