© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158638
    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_2_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
     on
    1.05
    don
    0.91
     функция
    0.91
    a
    0.87
    dır
    0.86
     eyeb
    0.83
     powied
    0.82
     বলিল
    0.82
    like
    0.81
     তুলনায়
    0.81
    POSITIVE LOGITS
    OT
    1.40
    AK
    1.35
    يل
    1.23
    ă
    1.14
    ру
    1.13
    EL
    1.12
    EN
    1.11
    AT
    1.09
    ES
    1.09
    ура
    1.09
    Activations Density 0.000%

    No Known Activations