© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16288
    Prev
    Next
    INDEX
    Explanations

    German language text containing specific grammatical structures and references to Franz Kafka's "Der Prozess".

    oai_token-act-pair · gemini-2.0-flash

    German language

    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
    NewUrlParser
    -0.39
    mallow
    -0.38
    皮
    -0.37
    divarius
    -0.37
     se
    -0.36
     Nerv
    -0.36
    лин
    -0.36
    ような
    -0.36
    ficado
    -0.36
    ynn
    -0.35
    POSITIVE LOGITS
    expandindo
    0.71
     endwhile
    0.69
     كومونز
    0.68
    AndEndTag
    0.66
    stateProvider
    0.66
     ſtand
    0.66
    ("")]
    0.65
     beſt
    0.65
    andExpect
    0.65
    ſelf
    0.65
    Activations Density 0.455%

    No Known Activations