© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 18216
    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_34_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
     एलि
    0.41
    чни
    0.39
     ပ
    0.39
    údio
    0.38
    EventQueue
    0.38
    daction
    0.38
    ã
    0.37
    事で
    0.37
     Suit
    0.36
    っきり
    0.36
    POSITIVE LOGITS
     vasculature
    0.39
    }});
    0.39
    ciphertext
    0.39
    阈
    0.38
     فرن
    0.37
    peasants
    0.37
     calmness
    0.36
    拣
    0.36
     σχ
    0.36
     piglets
    0.36
    Activations Density 0.000%

    No Known Activations