© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12302
    Prev
    Next
    INDEX
    Explanations

    terms related to systems, features and support

    oai_token-act-pair · gemini-2.0-flash

    supported features

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     support
    -1.68
    support
    -1.38
     Support
    -1.24
    Support
    -1.16
     love
    -1.09
     supporto
    -0.98
     care
    -0.93
     soutien
    -0.91
     поддержку
    -0.90
    upport
    -0.89
    POSITIVE LOGITS
    ."</
    0.66
     werfen
    0.65
    __":
    0.63
     žiad
    0.61
    ResumeLayout
    0.60
    */;
    0.59
    })*/
    0.59
    ).</
    0.58
     žád
    0.58
    >",
    0.57
    Activations Density 4.891%

    No Known Activations