© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5433
    Prev
    Next
    INDEX
    Explanations

    scientific text mentioning a constant value modified by some process

    oai_token-act-pair · gemini-2.0-flash

    constant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     constant
    -2.78
    constant
    -2.41
     Constant
    -2.39
    Constant
    -2.25
     CONSTANT
    -2.19
     constante
    -2.05
     constantly
    -1.97
     constantes
    -1.95
     constants
    -1.88
     continual
    -1.87
    POSITIVE LOGITS
    хьтан
    0.60
    intios
    0.56
     calendriers
    0.53
    /******/
    0.49
     صوتيه
    0.47
    netbeans
    0.47
    ANDRO
    0.47
     ceci
    0.47
    ||||
    0.46
     насељу
    0.46
    Activations Density 3.860%

    No Known Activations