© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5342
    Prev
    Next
    INDEX
    Explanations

    terms related to Facebook's terms of service in Croatian

    oai_token-act-pair · gemini-2.0-flash

    foreign language or code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    })));
    -0.73
     Monfieur
    -0.72
     Anſ
    -0.72
    ientôt
    -0.71
     polaire
    -0.69
     OnInit
    -0.66
    úsqueda
    -0.66
     nadzieję
    -0.64
     épu
    -0.63
    towym
    -0.63
    POSITIVE LOGITS
    z
    0.50
     le
    0.49
    v
    0.44
     Le
    0.40
    lež
    0.40
    j
    0.40
    pravy
    0.39
     Z
    0.39
     R
    0.37
    znam
    0.36
    Activations Density 0.277%

    No Known Activations