INDEX

Explanations

closing curly brackets

oai_token-act-pair · gemini-2.0-flash

}

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyTitle

-0.93

 myſelf

-0.91

 leaſt

-0.87

 becauſe

-0.87

JspWriter

-0.86

 typelib

-0.85

 ſeveral

-0.85

ſelf

-0.85

ⓧ

-0.84

 quæ

-0.83

POSITIVE LOGITS

0.49

et

0.46

 west

0.40

架

0.39

jam

0.38

<eos>

0.38

udi

0.38

Activations Density 0.316%

closing curly brackets

}

No Comments

No Known Activations