INDEX

Explanations

proper nouns, science and technology terms

oai_token-act-pair · 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

bus

-0.72

bus

-0.69

Bus

-0.63

 disponibilités

-0.61

Bus

-0.60

 chofe

-0.55

 poffe

-0.55

BUS

-0.53

rion

-0.52

 buses

-0.52

POSITIVE LOGITS

dafx

0.82

LEncoder

0.68

/**

0.60

endphp

0.59

Explicación

0.58

kháu

0.57

MessageTagHelper

0.57

ParallelGroup

0.55

Xna

0.54

SOUNDBITE

0.53

Activations Density 12.231%

proper nouns, science and technology terms

No Comments

No Known Activations