© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11924
    Prev
    Next
    INDEX
    Explanations

    the letter "s", and assigns a small positive value when the word "positive" occurs

    oai_token-act-pair · gemini-2.0-flash

    's'

    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
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -4.03
    ی
    -1.66
    t
    -1.35
    ים
    -1.34
    ся
    -1.29
    ы
    -1.22
    d
    -1.19
    ات
    -1.16
    sver
    -1.14
    es
    -1.11
    POSITIVE LOGITS
     дописавши
    1.04
    Manbalar
    0.99
     Chwiliwch
    0.96
    });*/
    0.91
     '\\;'
    0.88
     kaarangay
    0.85
    })*/
    0.84
     bezeichneter
    0.83
     aDecoder
    0.82
    RenderAtEndOf
    0.82
    Activations Density 2.002%

    No Known Activations