© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10678
    Prev
    Next
    INDEX
    Explanations

    the word "indicated" and some misspellings like "indications".

    oai_token-act-pair · gemini-2.0-flash

    indicated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     indicated
    -2.19
     indicate
    -2.02
    indicated
    -1.83
     indicates
    -1.83
     indicating
    -1.81
     INDIC
    -1.80
     indication
    -1.72
     indic
    -1.72
     Indic
    -1.68
    indic
    -1.63
    POSITIVE LOGITS
    
    0.93
     betweenstory
    0.79
    WebElementEntity
    0.77
    ьаж
    0.67
    seguida
    0.65
    stateProvider
    0.63
     Económica
    0.63
     OFDb
    0.63
    первых
    0.63
    ])));
    0.62
    Activations Density 1.786%

    No Known Activations