INDEX

Explanations

bio

np_max-act-logits · gemini-2.0-flash

words related to biology and academic studies/projects

oai_token-act-pair · gemini-2.0-flash

Bio or biological

np_token-act-pair-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

PROMOTED

-0.77

nościo

-0.69

 CreateTagHelper

-0.68

BufferException

-0.58

⌐

-0.54

clase

-0.53

igsaw

-0.53

raiser

-0.52

bootstrapcdn

-0.52

 vấn

-0.52

POSITIVE LOGITS

RegressionTest

0.60

ButtonModule

0.55

AndEndTag

0.53

/*

0.49

alı

0.49

IGraphics

0.48

 veau

0.47

 coster

0.45

 biel

0.44

joi

0.44

Activations Density 3.527%

bio

words related to biology and academic studies/projects

Bio or biological

No Comments

No Known Activations