© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41768
    Prev
    Next
    INDEX
    Explanations

    Freedom of movement

    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_3_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
    marginBottom
    0.67
     ۲
    0.63
    "
    0.57
    ۲
    0.55
    latex
    0.55
    ва
    0.53
    service
    0.53
     県
    0.53
    لی
    0.51
    ลง
    0.51
    POSITIVE LOGITS
     have
    0.84
     achieve
    0.70
    ell
    0.68
    Have
    0.68
     do
    0.66
     arrive
    0.66
    し
    0.65
     appear
    0.65
     continue
    0.65
     remain
    0.64
    Activations Density 0.000%

    No Known Activations