INDEX

Explanations

terms related to tumors and the progenitor cells that can turn into them.

oai_token-act-pair · gemini-2.0-flash

Medical and biological contexts

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 ویکی‌پدیای

-0.66

flashdata

-0.61

 excru

-0.58

(!__

-0.56

__":

-0.54

RefreshLayout

-0.48

CreateTable

-0.47

ensi

-0.45

期刊论文

-0.45

BASEPATH

-0.45

POSITIVE LOGITS

Zeneca

0.64

 espirituales

0.63

 boî

0.60

Coordonnées

0.56

 estimés

0.56

featureID

0.55

 marinho

0.55

 voks

0.54

RuleContext

0.52

 démocr

0.52

Activations Density 2.824%

terms related to tumors and the progenitor cells that can turn into them.

Medical and biological contexts

No Comments

No Known Activations