© 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. 169294
    Prev
    Next
    INDEX
    Explanations

    Polish language

    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
     ó
    0.89
     Ó
    0.73
    ika
    0.69
    ós
    0.65
    Ó
    0.59
    IKA
    0.58
     ό
    0.52
     ò
    0.52
    ó
    0.51
     ic
    0.50
    POSITIVE LOGITS
     mal
    0.40
    澤
    0.37
    Ist
    0.37
    百
    0.36
     રાજ્ય
    0.35
     pendulum
    0.34
    iore
    0.33
    Invent
    0.33
     Schrö
    0.33
     rownames
    0.33
    Activations Density 0.001%

    No Known Activations