© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1204
    Prev
    Next
    INDEX
    Explanations

    the string "mam" or fragments of sentences in Croatian

    oai_token-act-pair · gemini-2.0-flash

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     AssemblyCulture
    -0.85
    tagHelperRunner
    -0.84
    IntoConstraints
    -0.81
     виправивши
    -0.79
     ujednoznacz
    -0.69
     ویکی‌پدیا
    -0.66
    SharedDtor
    -0.66
    脚注の使い方
    -0.66
    PyExc
    -0.66
    NOPQRST
    -0.66
    POSITIVE LOGITS
     jsme
    0.58
     będziemy
    0.56
     mať
    0.55
     ktoś
    0.54
     będę
    0.54
     mogę
    0.53
     bowiem
    0.52
     Somit
    0.52
     będziesz
    0.52
     jesteśmy
    0.52
    Activations Density 0.439%

    No Known Activations