© 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. 6949
    Prev
    Next
    INDEX
    Explanations

    various code snippets and mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    Code and figures

    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
    '];?>
    -0.60
    ']?>
    -0.56
    }
    -0.52
     sur
    -0.50
    .}
    -0.49
    ?>
    -0.49
    };
    -0.49
    */
    -0.48
    /**
    -0.48
     compound
    -0.46
    POSITIVE LOGITS
    PerformLayout
    0.72
    DebuggerNonUser
    0.66
    GEBURTS
    0.65
    WaitGroup
    0.65
    coroutines
    0.65
    RUnlock
    0.60
     itſelf
    0.59
    mybatisplus
    0.58
    ########.
    0.58
    scalatest
    0.57
    Activations Density 4.180%

    No Known Activations