© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 216969
    Prev
    Next
    INDEX
    Explanations

    old man [name] the [role]

    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_31_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
    TERS
    0.41
    IRED
    0.40
    ANTI
    0.40
    OTO
    0.39
    ETER
    0.39
    Neither
    0.39
    ]`
    0.39
    Try
    0.38
    Tram
    0.38
    Joseph
    0.37
    POSITIVE LOGITS
     township
    0.40
     pertinent
    0.37
     обстоятельства
    0.37
     socios
    0.36
     autochtones
    0.35
     awesome
    0.35
     notches
    0.35
    ㄺ
    0.34
    茯
    0.34
     townships
    0.34
    Activations Density 0.004%

    No Known Activations