INDEX

Explanations

words related to communication, delays, or reactions to something said.

oai_token-act-pair · gemini-2.0-flash

conversation about withholding information

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 незавершена

-0.58

 MainAxisSize

-0.57

WriteBarrier

-0.57

TagMode

-0.56

Примітки

-0.54

BindingSource

-0.54

 beginnetje

-0.53

`}

-0.53

 TextAlign

-0.53

ImageContext

-0.52

POSITIVE LOGITS

OCCURRED

0.57

 урна

0.54

 <<<<<<<<<<<<<<

0.48

djangoproject

0.48

principalTable

0.46

дожник

0.46

 esternos

0.46

Nationalité

0.46

loin

0.46

WebMethod

0.45

Activations Density 0.262%

words related to communication, delays, or reactions to something said.

conversation about withholding information

No Known Activations