© 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. 6701
    Prev
    Next
    INDEX
    Explanations

    phrases where the author is recommending something

    oai_token-act-pair · gemini-2.0-flash

    Recommendations and support

    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
     Highly
    -1.19
    Highly
    -1.18
    highly
    -1.15
     highly
    -1.11
     myſelf
    -0.74
    abestanden
    -0.70
     beginnetje
    -0.69
    存于互联网档案馆
    -0.69
    IntoConstraints
    -0.69
     >=",
    -0.69
    POSITIVE LOGITS
    žová
    0.49
     su
    0.48
    Rek
    0.47
    mstyle
    0.45
    代
    0.44
    1
    0.42
     sui
    0.42
    enko
    0.40
     ad
    0.40
    دهم
    0.40
    Activations Density 0.509%

    No Known Activations