INDEX

Explanations

code-related keywords such as "return", "throw", and unbalanced curly brackets

oai_token-act-pair · gemini-2.0-flash

code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

main

-0.45

Geografi

-0.44

 Esposito

-0.43

("%

-0.42

urati

-0.42

 main

-0.42

Affirmed

-0.42

AFFIRMED

-0.41

 Tatsache

-0.40

람

-0.40

POSITIVE LOGITS

 >=",

0.88

 AssemblyTitle

0.75

 bezeichneter

0.65

NewUrlParser

0.63

таратура

0.58

GTCX

0.57

testcase

0.56

enterOuterAlt

0.55

FunctionFlags

0.55

новниш

0.53

Activations Density 0.328%

code-related keywords such as "return", "throw", and unbalanced curly brackets

code snippets

No Comments

No Known Activations