INDEX

Explanations

words related to genetics, diseases, and medical diagnoses

oai_token-act-pair · gemini-2.0-flash

genetic mutations and diseases

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 صوتيه

-0.72

UrlResolution

-0.71

tvguidetime

-0.68

RenderAtEndOf

-0.67

 ujednoznacz

-0.66

 médec

-0.61

 μεγ

-0.61

berdayakan

-0.60

ITICAL

-0.58

rogenic

-0.57

POSITIVE LOGITS

IsMutable

0.55

JMenuBar

0.47

<",

0.46

তথ্যসূত্র

0.44

Jegyzetek

0.44

Przypisy

0.42

 }}">

0.42

%>

0.42

 {}));

0.41

WRC

0.41

Activations Density 4.868%

words related to genetics, diseases, and medical diagnoses

genetic mutations and diseases

No Comments

No Known Activations