© 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-3-4B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 2701
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ки
    2.92
    ➔
    2.50
     ami
    2.48
    gripper
    2.48
    सभा
    2.40
     suspect
    2.40
    ণের
    2.34
     gql
    2.33
    nament
    2.28
    }[[
    2.23
    POSITIVE LOGITS
    Deze
    2.56
    ছি
    2.56
    Rough
    2.53
    ll
    2.51
     Electrons
    2.50
    মাণ
    2.37
    it
    2.37
    ছিলাম
    2.35
     lãi
    2.33
    बर
    2.33
    Activations Density 0.006%

    No Known Activations