© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165420
    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_31_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
     gasped
    0.42
     haul
    0.39
     journey
    0.37
     risky
    0.37
    }$&$-
    0.37
     Hawai
    0.37
     निका
    0.37
     inl
    0.37
    िशियल
    0.36
     landing
    0.36
    POSITIVE LOGITS
    hat
    0.44
    aryn
    0.43
    Acc
    0.42
    Adv
    0.40
    飩
    0.39
    adv
    0.39
    Anche
    0.38
    ının
    0.37
    Hat
    0.37
    rania
    0.36
    Activations Density 0.000%

    No Known Activations