© 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. 12-GEMMASCOPE-2-TRANSCODER-16K
    7. 1197
    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_12_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
     فرمان
    0.31
    ང
    0.30
     അമ്മ
    0.29
     NPTypeCode
    0.29
    엮
    0.29
    <unused570>
    0.27
    ေ့
    0.27
    Leave
    0.27
    ngày
    0.27
    য়োজন
    0.27
    POSITIVE LOGITS
     standby
    0.29
     clerical
    0.29
    чью
    0.28
     Algun
    0.28
     inlet
    0.27
     majority
    0.27
    ἷ
    0.26
     nostro
    0.26
     kita
    0.26
    Edd
    0.26
    Activations Density 0.442%

    No Known Activations