© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12578
    Prev
    Next
    INDEX
    Explanations

    locations, times and logistics related to train travel being disrupted by political events

    oai_token-act-pair · gemini-2.0-flash

    Railway stations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bezeichneter
    -0.61
     muerta
    -0.49
    ध्य
    -0.48
    oss
    -0.48
     industriale
    -0.47
    enderror
    -0.47
     ويكي
    -0.46
    IActionResult
    -0.46
    ArgsConstructor
    -0.45
    脚注の使い方
    -0.45
    POSITIVE LOGITS
    SPATH
    0.60
     Platform
    0.58
    +#+#
    0.58
    IBUS
    0.55
    Hentet
    0.55
    helf
    0.54
     חיצוניים
    0.53
    fromCharCode
    0.53
    Priv
    0.50
     platform
    0.50
    Activations Density 0.355%

    No Known Activations