INDEX

Explanations

gene names and words associated with scientific research

oai_token-act-pair · gemini-2.0-flash

causing/causes

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

 vực

-0.63

ArrowToggle

-0.60

mamış

-0.56

 autorytatywna

-0.55

 Filling

-0.54

Efq

-0.53

lename

-0.53

drawiam

-0.52

Mug

-0.52

reducible

-0.51

POSITIVE LOGITS

 causing

0.64

 causes

0.60

 provoquer

0.54

causing

0.54

 menyebabkan

0.53

causes

0.52

EndContext

0.52

 cause

0.52

PYX

0.50

 صوتيه

0.50

Activations Density 2.744%

gene names and words associated with scientific research

causing/causes

No Comments

No Known Activations

gene names and words associated with scientific research

causing/causes

No Comments

No Known Activations