© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 258838
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_22_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
    arius
    0.46
    1
    0.46
    A
    0.46
    াঙ্গ
    0.41
    G
    0.41
    C
    0.40
    n
    0.40
    ن
    0.40
    B
    0.39
    pores
    0.39
    POSITIVE LOGITS
     absences
    0.55
     welchem
    0.55
     bekannte
    0.52
    𝖐
    0.51
     zum
    0.50
     posta
    0.49
     bekannten
    0.49
     układ
    0.49
     faktor
    0.49
     pouquinho
    0.48
    Activations Density 0.000%

    No Known Activations