© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 152141
    Prev
    Next
    INDEX
    Explanations

    Machine

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    >)
    0.59
    })
    0.59
    "})
    0.55
    )}
    0.54
    )}^{\
    0.54
     })
    0.53
    )<\
    0.52
    })$
    0.52
    )}{
    0.51
    )}=
    0.51
    POSITIVE LOGITS
     texting
    0.55
     text
    0.48
     textual
    0.45
     zooming
    0.42
     Text
    0.42
     homeschooling
    0.41
     darker
    0.40
     Mogo
    0.40
     legal
    0.39
     trolling
    0.39
    Activations Density 0.000%

    No Known Activations