© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 213940
    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_5_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
    s
    1.30
    ం
    1.23
    r
    1.23
    d
    1.22
    sen
    1.17
    b
    1.13
    ل
    1.09
    dreams
    1.05
    sl
    1.04
    dream
    1.02
    POSITIVE LOGITS
    in
    1.66
    ARI
    1.16
    ↵
    1.13
     cheio
    1.08
     incend
    1.07
    AN
    1.05
     данни
    1.05
     informar
    1.04
     dotato
    1.04
     realiz
    1.03
    Activations Density 0.000%

    No Known Activations