© 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. 6440
    Prev
    Next
    INDEX
    Explanations

    statements introducing a problem, or making a nuanced statement about something generally positive

    oai_token-act-pair · gemini-2.0-flash

    Existence of problems/deficiencies

    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
     remains
    -2.09
    remains
    -1.88
     Remains
    -1.79
     remain
    -1.74
    remain
    -1.58
     Still
    -1.49
     continues
    -1.49
     remained
    -1.48
    Still
    -1.45
     remaining
    -1.44
    POSITIVE LOGITS
    /**
    0.72
    WriteBarrier
    0.69
    writeHead
    0.59
    WithEmail
    0.57
    ItemLayout
    0.57
     sinned
    0.57
    antMatchers
    0.57
    saraba
    0.56
    Diwedd
    0.56
     />;
    0.55
    Activations Density 0.698%

    No Known Activations