INDEX

Explanations

C++ code

oai_token-act-pair · gemini-2.0-flash

std

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

évaluateur

-0.82

contentLoaded

-0.74

IndentedString

-0.70

 متعلقه

-0.66

TypedDataSet

-0.65

 оригіналу

-0.63

 Meksiku

-0.61

ModelSerializer

-0.61

IsContent

-0.61

*)(

-0.61

POSITIVE LOGITS

月号

0.45

Bronnen

0.43

NewLabel

0.41

 aspet

0.40

Filmographie

0.40

endphp

0.40

urbo

0.40

amssymb

0.40

drawing

0.40

 weshalb

0.40

Activations Density 0.196%

C++ code

std

No Comments

No Known Activations