© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 167100
    Prev
    Next
    INDEX
    Explanations

    very/incredibly + positive adjective

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     créée
    0.36
     asigur
    0.36
     created
    0.35
    更容易
    0.35
     noun
    0.35
     Created
    0.34
     쉽
    0.34
    是中国
    0.33
     reservation
    0.32
    易
    0.32
    POSITIVE LOGITS
    чайно
    0.48
     আলোর
    0.40
    udarstven
    0.40
     Remedies
    0.38
     použí
    0.38
     ব্যাবহার
    0.37
     डालने
    0.36
    ਣਾ
    0.36
     হয়েছিলো
    0.36
     obedient
    0.35
    Activations Density 0.009%

    No Known Activations