© 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. 2885
    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
    ן
    3.48
    ל
    2.81
    ার
    2.77
    erade
    2.67
    ه
    2.63
    ν
    2.49
    ה
    2.45
     direitos
    2.43
    させる
    2.43
    }$.
    2.40
    POSITIVE LOGITS
    et
    2.98
     तौर
    2.89
    ted
    2.86
    kf
    2.76
    ัพท์
    2.68
    hh
    2.64
    preds
    2.63
    ties
    2.63
     elems
    2.60
    lifting
    2.59
    Activations Density 0.006%

    No Known Activations