© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13315
    Prev
    Next
    INDEX
    Explanations

    the word "plan", but also sometimes the word "part" and words related to the concept of "need".

    oai_token-act-pair · gemini-2.0-flash

    plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ]));
    -1.05
     Roskov
    -1.03
    rungsseite
    -1.03
     nahilalakip
    -1.02
    complexContent
    -0.97
    ")));
    -0.96
    )";
    -0.93
     tartalomajánló
    -0.92
    новниш
    -0.92
    )));
    -0.91
    POSITIVE LOGITS
    明
    0.58
    直
    0.55
    架
    0.54
    似
    0.52
    Fields
    0.51
    무
    0.51
     base
    0.49
     Dank
    0.48
    miştir
    0.48
    uai
    0.48
    Activations Density 0.551%

    No Known Activations