INDEX

Explanations

the word "buffer" sometimes adjacent to other words related to computing

oai_token-act-pair · gemini-2.0-flash

buffer

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 buffer

-1.96

buffer

-1.95

 Buffer

-1.77

Buffer

-1.77

 buffers

-1.42

BUFFER

-1.34

 BUFFER

-1.13

Buffers

-1.09

buffers

-1.09

缓冲

-1.06

POSITIVE LOGITS

 autorytatywna

1.02

 betweenstory

0.98

GEBURTSDATUM

0.93

 faſt

0.92

 pleaſure

0.91

 Jefus

0.91

 Diſ

0.90

 myſelf

0.90

 Majefty

0.90

 Monfieur

0.90

Activations Density 0.738%

the word "buffer" sometimes adjacent to other words related to computing

buffer

No Known Activations