INDEX

Explanations

technical writing, specifically related to measurement values and scientific analysis

oai_token-act-pair · gemini-2.0-flash

micro

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

 collè

-0.54

contentLoaded

-0.51

ServletException

-0.48

NamedQuery

-0.47

GeoNames

-0.47

 langage

-0.44

elemField

-0.43

Man

-0.43

addHandler

-0.42

jsonwebtoken

-0.42

POSITIVE LOGITS

 otomatig

0.71

 micro

0.69

Personendaten

0.69

 micron

0.69

mic

0.68

 microns

0.68

µ

0.67

micro

0.66

\{\\

0.66

 Micro

0.65

Activations Density 2.551%

technical writing, specifically related to measurement values and scientific analysis

micro

No Comments

No Known Activations