© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12597
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to the levels or tiers in a game

    oai_token-act-pair · gemini-2.0-flash

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    Level
    -0.80
     Level
    -0.74
     Levels
    -0.58
    LEVEL
    -0.56
    Levels
    -0.53
    level
    -0.52
     LEVEL
    -0.52
    NegativeButton
    -0.46
    '
    -0.46
    Nivel
    -0.46
    POSITIVE LOGITS
     itſelf
    0.81
     myſelf
    0.78
     ſtate
    0.77
     purpoſe
    0.76
     CanadaChoose
    0.75
     Diſ
    0.75
     himſelf
    0.74
     CWE
    0.73
     Roskov
    0.71
    новниш
    0.68
    Activations Density 0.325%

    No Known Activations