© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 147878
    Prev
    Next
    INDEX
    Explanations

    chatting and talking

    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_18_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
    ágina
    0.44
    á
    0.43
    seti
    0.42
    ā
    0.42
    umi
    0.41
    ré
    0.41
    メガネ
    0.40
    si
    0.40
    sy
    0.40
    auté
    0.39
    POSITIVE LOGITS
     imposed
    0.46
     encompassed
    0.46
    eight
    0.44
     agribusiness
    0.44
     delivered
    0.44
     kwenye
    0.42
    ዕ
    0.42
     currency
    0.42
     accommodated
    0.42
     loaded
    0.41
    Activations Density 0.004%

    No Known Activations