© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201551
    Prev
    Next
    INDEX
    Explanations

    use

    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_37_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
     needles
    0.64
     Needle
    0.49
     circulaire
    0.47
     needle
    0.46
    针
    0.46
     monumento
    0.43
    circular
    0.43
     circular
    0.42
    針
    0.42
     peaceful
    0.40
    POSITIVE LOGITS
     weak
    0.93
     Weak
    0.92
    Weak
    0.90
    weak
    0.84
    弱
    0.80
     слабы
    0.71
     weaken
    0.69
     weaker
    0.68
     দুর্বল
    0.64
     weakness
    0.64
    Activations Density 0.000%

    No Known Activations