INDEX

Explanations

common words, technical terms and proper nouns

oai_token-act-pair · 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

Not in Any Lists

No Comments

Negative Logits

principalColumn

-0.70

 Theſe

-0.60

 MessageBoxIcon

-0.59

ItemLayout

-0.58

Efq

-0.57

 HasFactory

-0.57

SerializedSize

-0.54

 ſmall

-0.54

InitVars

-0.53

potranspiration

-0.53

POSITIVE LOGITS

<bos>

0.90

0.54

 Paglinawan

0.52

SourceChecksum

0.48

GraphicsUnit

0.47

 AttributeSet

0.45

sin

0.42

lis

0.41

nloa

0.40

 مرئيه

0.40

Activations Density 5.410%

common words, technical terms and proper nouns

No Comments

No Known Activations