INDEX

Explanations

technical scientific terms, often found in research papers and medical reports with emphasis on biology and chemistry terms

oai_token-act-pair · gemini-2.0-flash

Prefixes

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

 Inscrivez

-0.31

 AQUÍ

-0.30

kej

-0.27

neſs

-0.26

 pitié

-0.26

 Diſ

-0.26

 vertes

-0.25

 quæ

-0.25

ſelf

-0.25

 AQUI

-0.23

POSITIVE LOGITS

clearance

0.82

transportation

0.82

regime

0.79

substrate

0.78

decomposition

0.78

productive

0.77

administrative

0.77

theoretical

0.77

curriculum

0.77

calibration

0.77

Activations Density 17.656%

technical scientific terms, often found in research papers and medical reports with emphasis on biology and chemistry terms

Prefixes

No Comments

No Known Activations