INDEX

Explanations

question asking for help or advice with phrases like "any one," "help me," and "let me know."

oai_token-act-pair · gemini-2.0-flash

Any

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

ритори

-0.54

BuildContext

-0.54

 FetchType

-0.46

 körül

-0.46

essoas

-0.46

Зноскі

-0.45

 brancas

-0.45

eland

-0.44

$")

-0.44

printLine

-0.44

POSITIVE LOGITS

 thing

2.00

 THING

1.43

 Thing

1.35

Thing

1.17

 body

1.05

 where

1.04

thing

1.04

body

0.81

Body

0.75

 Body

0.74

Activations Density 4.010%

question asking for help or advice with phrases like "any one," "help me," and "let me know."

Any

No Comments

No Known Activations

question asking for help or advice with phrases like "any one," "help me," and "let me know."

Any

No Comments

No Known Activations