INDEX

Explanations

text containing code examples coupled with predicted output and the words "guess", "think", or "know"

oai_token-act-pair · gemini-2.0-flash

output, guess, response

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

localPosition

-0.46

 NACIONAL

-0.44

 Nacional

-0.43

 jossa

-0.42

 recensement

-0.42

 incó

-0.42

RunAsync

-0.41

 sauvage

-0.41

 DialogInterface

-0.41

SizeMode

-0.41

POSITIVE LOGITS

 مشين

0.95

Autoritní

0.79

 oprot

0.77

endphp

0.70

 autorytatywna

0.65

 indisponible

0.65

 snippetHide

0.64

ofire

0.63

__":

0.62

 通販

0.62

Activations Density 1.557%

text containing code examples coupled with predicted output and the words "guess", "think", or "know"

output, guess, response

No Comments

No Known Activations