INDEX

Explanations

references to news broadcasts

oai_token-act-pair · gemini-2.0-flash

casts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 pinulongan

-0.48

ArgsConstructor

-0.45

INCREF

-0.44

eip

-0.42

wordpress

-0.42

DriverManager

-0.41

himu

-0.41

 filosofía

-0.41

VILL

-0.41

WebElementEntity

-0.40

POSITIVE LOGITS

<bos>

1.52

 televis

0.79

 broadcast

0.76

 broadcasters

0.74

 television

0.73

 broadcasts

0.72

 himſelf

0.71

 chofe

0.71

 raiſ

0.71

 fhew

0.70

Activations Density 0.547%

references to news broadcasts

casts

No Comments

No Known Activations