© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14056
    Prev
    Next
    INDEX
    Explanations

    timestamps, or numbers followed by "am"/"pm"

    oai_token-act-pair · gemini-2.0-flash

    Times/Schedules

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    aga
    -0.50
    sc
    -0.49
    N
    -0.49
    к
    -0.49
    DP
    -0.48
    Sc
    -0.48
    aj
    -0.48
    O
    -0.48
    No
    -0.47
    External
    -0.47
    POSITIVE LOGITS
    rungsseite
    1.02
     AssemblyTitle
    0.99
    __':
    0.88
    "]);
    0.85
    CloseOperation
    0.81
    脚注の使い方
    0.79
     gynnwys
    0.79
    ]")]
    0.75
    contentLoaded
    0.73
    LLocation
    0.73
    Activations Density 0.524%

    No Known Activations