© 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. 14613
    Prev
    Next
    INDEX
    Explanations

    text found in internet chat logs, specifically lines starting with greater-than signs and potentially user names encased in angle brackets

    oai_token-act-pair · gemini-2.0-flash

    Programming-related questions

    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
    A
    -1.02
    a
    -1.02
    The
    -1.00
    We
    -0.91
    2
    -0.90
    ‘
    -0.89
    An
    -0.88
    For
    -0.87
    the
    -0.86
    In
    -0.86
    POSITIVE LOGITS
    CHREIB
    0.61
    PERTIES
    0.60
    mbggenerated
    0.59
    CppMethod
    0.59
    ETRIC
    0.56
    UAGE
    0.56
    ADORES
    0.56
    VELOP
    0.56
    ChildScrollView
    0.56
    VIRON
    0.55
    Activations Density 6.168%

    No Known Activations