© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117561
    Prev
    Next
    INDEX
    Explanations

    We followed by auxiliary verbs

    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_27_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
    Neil
    0.38
    Profiling
    0.36
    Skills
    0.35
    にします
    0.35
    Progress
    0.35
    錡
    0.34
    婄
    0.34
    Setting
    0.34
     เบ
    0.34
    妝
    0.33
    POSITIVE LOGITS
     aptly
    0.40
     confirmó
    0.39
    ocond
    0.39
     totally
    0.38
    subsec
    0.38
     сво
    0.37
    wegian
    0.37
    odoro
    0.37
    ovsk
    0.37
    身
    0.36
    Activations Density 0.004%

    No Known Activations