© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208234
    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_25_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
    უდ
    0.41
    overe
    0.40
     overcome
    0.38
    jl
    0.38
    ♫
    0.38
    ენტ
    0.37
    ítani
    0.37
    олові
    0.36
    ᖕ
    0.36
     konstru
    0.36
    POSITIVE LOGITS
    其他
    0.36
    他の
    0.36
     diğer
    0.35
     TD
    0.35
     Triple
    0.35
     другие
    0.35
     other
    0.34
     اندازه
    0.34
     Nutz
    0.34
     इतर
    0.34
    Activations Density 0.000%

    No Known Activations