INDEX

Explanations

code or markup, especially delimiters

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

<bos>

-1.25

-0.74

↵

-0.64

’

-0.60

-0.58

the

-0.56

-0.54

-0.52

on

-0.52

POSITIVE LOGITS

NameInMap

1.00

Vidite

0.95

principalColumn

0.88

UserScript

0.87

 مرئيه

0.86

webElementXpaths

0.86

parsedMessage

0.85

PerformLayout

0.85

 Roskov

0.84

 initComponents

0.84

Activations Density 0.789%

code or markup, especially delimiters

No Comments

No Known Activations