© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 34345
    Prev
    Next
    INDEX
    Explanations

    get rid of / eliminate

    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
    ophile
    0.46
    odet
    0.40
    ্থ
    0.39
     શકો
    0.39
    odhpur
    0.39
    ᾿
    0.38
    ots
    0.38
    ètent
    0.38
     করো
    0.37
    ophilic
    0.36
    POSITIVE LOGITS
     tertarik
    0.43
     directo
    0.38
     senang
    0.38
     encant
    0.38
     manutenção
    0.38
    щину
    0.37
     interesado
    0.36
     cert
    0.35
     produkcji
    0.35
    㑅
    0.35
    Activations Density 0.009%

    No Known Activations