© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 3049
    Prev
    Next
    INDEX
    Explanations

    mentions of "we" and "us" related to a study

    oai_token-act-pair · gemini-2.0-flash

    We

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     disponibilités
    -0.76
    UserScript
    -0.63
    日至
    -0.56
    UnsafeEnabled
    -0.55
     defStyleAttr
    -0.54
    ImageContext
    -0.54
     []),
    -0.54
     فريبيس
    -0.54
    []):
    -0.53
    "]();
    -0.53
    POSITIVE LOGITS
    unos
    0.48
    RetentionPolicy
    0.47
     centralized
    0.46
    setViewportView
    0.46
    AnchorStyles
    0.46
    EDEFAULT
    0.44
    tai
    0.44
     Loa
    0.44
    Slim
    0.43
    PIA
    0.43
    Activations Density 4.500%

    No Known Activations