INDEX

Explanations

Japanese phrases related to seeking clarification or assistance.

oai_token-act-pair · gemini-2.0-flash

multiple languages

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

opia

-0.51

だ

-0.44

op

-0.44

 vär

-0.43

からです

-0.43

</em>

-0.42

功

-0.41

hek

-0.41

later

-0.41

POSITIVE LOGITS

 Shakspeare

0.82

 Cæsar

0.70

 noDo

0.69

 Monfieur

0.68

 Shaksp

0.68

 myſelf

0.68

styleUrls

0.67

InputBorder

0.66

省市镇

0.66

LayoutPanel

0.65

Activations Density 0.317%

Japanese phrases related to seeking clarification or assistance.

multiple languages

No Comments

No Known Activations