© 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
    2. Gemma-2-2B
    3. 6-GEMMASCOPE-TRANSCODER-16K
    4. 13260
    Prev
    Next
    INDEX
    Explanations

    instances of time and location references, often near the words "of" and "the".

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    +#+#
    -0.55
    Clik
    -0.52
     propOrder
    -0.51
    ftagPool
    -0.47
    AsUp
    -0.47
    NameInMap
    -0.46
     ContentValues
    -0.46
    RegressionTest
    -0.46
    lwjgl
    -0.45
    جانب
    -0.44
    POSITIVE LOGITS
     qed
    0.68
    ]--;
    0.67
     ioutil
    0.65
    "]);
    
    0.63
    CodedInputStream
    0.62
     Monfieur
    0.62
    capulco
    0.62
    itoneal
    0.61
    UnknownFields
    0.61
    ])));
    0.60
    Activations Density 23.165%

    No Known Activations